Search

Your search keyword '"Stanczyk A"' showing total 5,142 results
Start Over Author "Stanczyk A"
5,142 results on '"Stanczyk A"'

1. Gemma 2: Improving Open Language Models at a Practical Size

Author

Gemma Team, Riviere, Morgane, Pathak, Shreya, Sessa, Pier Giuseppe, Hardin, Cassidy, Bhupatiraju, Surya, Hussenot, Léonard, Mesnard, Thomas, Shahriari, Bobak, Ramé, Alexandre, Ferret, Johan, Liu, Peter, Tafti, Pouya, Friesen, Abe, Casbon, Michelle, Ramos, Sabela, Kumar, Ravin, Lan, Charline Le, Jerome, Sammy, Tsitsulin, Anton, Vieillard, Nino, Stanczyk, Piotr, Girgin, Sertan, Momchev, Nikola, Hoffman, Matt, Thakoor, Shantanu, Grill, Jean-Bastien, Neyshabur, Behnam, Bachem, Olivier, Walton, Alanna, Severyn, Aliaksei, Parrish, Alicia, Ahmad, Aliya, Hutchison, Allen, Abdagic, Alvin, Carl, Amanda, Shen, Amy, Brock, Andy, Coenen, Andy, Laforge, Anthony, Paterson, Antonia, Bastian, Ben, Piot, Bilal, Wu, Bo, Royal, Brandon, Chen, Charlie, Kumar, Chintu, Perry, Chris, Welty, Chris, Choquette-Choo, Christopher A., Sinopalnikov, Danila, Weinberger, David, Vijaykumar, Dimple, Rogozińska, Dominika, Herbison, Dustin, Bandy, Elisa, Wang, Emma, Noland, Eric, Moreira, Erica, Senter, Evan, Eltyshev, Evgenii, Visin, Francesco, Rasskin, Gabriel, Wei, Gary, Cameron, Glenn, Martins, Gus, Hashemi, Hadi, Klimczak-Plucińska, Hanna, Batra, Harleen, Dhand, Harsh, Nardini, Ivan, Mein, Jacinda, Zhou, Jack, Svensson, James, Stanway, Jeff, Chan, Jetha, Zhou, Jin Peng, Carrasqueira, Joana, Iljazi, Joana, Becker, Jocelyn, Fernandez, Joe, van Amersfoort, Joost, Gordon, Josh, Lipschultz, Josh, Newlan, Josh, Ji, Ju-yeong, Mohamed, Kareem, Badola, Kartikeya, Black, Kat, Millican, Katie, McDonell, Keelin, Nguyen, Kelvin, Sodhia, Kiranbir, Greene, Kish, Sjoesund, Lars Lowe, Usui, Lauren, Sifre, Laurent, Heuermann, Lena, Lago, Leticia, McNealus, Lilly, Soares, Livio Baldini, Kilpatrick, Logan, Dixon, Lucas, Martins, Luciano, Reid, Machel, Singh, Manvinder, Iverson, Mark, Görner, Martin, Velloso, Mat, Wirth, Mateo, Davidow, Matt, Miller, Matt, Rahtz, Matthew, Watson, Matthew, Risdal, Meg, Kazemi, Mehran, Moynihan, Michael, Zhang, Ming, Kahng, Minsuk, Park, Minwoo, Rahman, Mofi, Khatwani, Mohit, Dao, Natalie, Bardoliwalla, Nenshad, Devanathan, Nesh, Dumai, Neta, Chauhan, Nilay, Wahltinez, Oscar, Botarda, Pankil, Barnes, Parker, Barham, Paul, Michel, Paul, Jin, Pengchong, Georgiev, Petko, Culliton, Phil, Kuppala, Pradeep, Comanescu, Ramona, Merhej, Ramona, Jana, Reena, Rokni, Reza Ardeshir, Agarwal, Rishabh, Mullins, Ryan, Saadat, Samaneh, Carthy, Sara Mc, Perrin, Sarah, Arnold, Sébastien M. R., Krause, Sebastian, Dai, Shengyang, Garg, Shruti, Sheth, Shruti, Ronstrom, Sue, Chan, Susan, Jordan, Timothy, Yu, Ting, Eccles, Tom, Hennigan, Tom, Kocisky, Tomas, Doshi, Tulsee, Jain, Vihan, Yadav, Vikas, Meshram, Vilobh, Dharmadhikari, Vishal, Barkley, Warren, Wei, Wei, Ye, Wenming, Han, Woohyun, Kwon, Woosuk, Xu, Xiang, Shen, Zhe, Gong, Zhitao, Wei, Zichuan, Cotruta, Victor, Kirk, Phoebe, Rao, Anand, Giang, Minh, Peran, Ludovic, Warkentin, Tris, Collins, Eli, Barral, Joelle, Ghahramani, Zoubin, Hadsell, Raia, Sculley, D., Banks, Jeanine, Dragan, Anca, Petrov, Slav, Vinyals, Oriol, Dean, Jeff, Hassabis, Demis, Kavukcuoglu, Koray, Farabet, Clement, Buchatskaya, Elena, Borgeaud, Sebastian, Fiedel, Noah, Joulin, Armand, Kenealy, Kathleen, Dadashi, Robert, and Andreev, Alek

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence
Abstract

In this work, we introduce Gemma 2, a new addition to the Gemma family of lightweight, state-of-the-art open models, ranging in scale from 2 billion to 27 billion parameters. In this new version, we apply several known technical modifications to the Transformer architecture, such as interleaving local-global attentions (Beltagy et al., 2020a) and group-query attention (Ainslie et al., 2023). We also train the 2B and 9B models with knowledge distillation (Hinton et al., 2015) instead of next token prediction. The resulting models deliver the best performance for their size, and even offer competitive alternatives to models that are 2-3 times bigger. We release all our models to the community.

Published
2024

2. BOND: Aligning LLMs with Best-of-N Distillation

Author

Sessa, Pier Giuseppe, Dadashi, Robert, Hussenot, Léonard, Ferret, Johan, Vieillard, Nino, Ramé, Alexandre, Shariari, Bobak, Perrin, Sarah, Friesen, Abe, Cideron, Geoffrey, Girgin, Sertan, Stanczyk, Piotr, Michi, Andrea, Sinopalnikov, Danila, Ramos, Sabela, Héliou, Amélie, Severyn, Aliaksei, Hoffman, Matt, Momchev, Nikola, and Bachem, Olivier

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computation and Language
Abstract

Reinforcement learning from human feedback (RLHF) is a key driver of quality and safety in state-of-the-art large language models. Yet, a surprisingly simple and strong inference-time strategy is Best-of-N sampling that selects the best generation among N candidates. In this paper, we propose Best-of-N Distillation (BOND), a novel RLHF algorithm that seeks to emulate Best-of-N but without its significant computational overhead at inference time. Specifically, BOND is a distribution matching algorithm that forces the distribution of generations from the policy to get closer to the Best-of-N distribution. We use the Jeffreys divergence (a linear combination of forward and backward KL) to balance between mode-covering and mode-seeking behavior, and derive an iterative formulation that utilizes a moving anchor for efficiency. We demonstrate the effectiveness of our approach and several design choices through experiments on abstractive summarization and Gemma models. Aligning Gemma policies with BOND outperforms other RLHF algorithms by improving results on several benchmarks.

Published
2024

3. Gemini: A Family of Highly Capable Multimodal Models

Author

Gemini Team, Anil, Rohan, Borgeaud, Sebastian, Alayrac, Jean-Baptiste, Yu, Jiahui, Soricut, Radu, Schalkwyk, Johan, Dai, Andrew M., Hauth, Anja, Millican, Katie, Silver, David, Johnson, Melvin, Antonoglou, Ioannis, Schrittwieser, Julian, Glaese, Amelia, Chen, Jilin, Pitler, Emily, Lillicrap, Timothy, Lazaridou, Angeliki, Firat, Orhan, Molloy, James, Isard, Michael, Barham, Paul R., Hennigan, Tom, Lee, Benjamin, Viola, Fabio, Reynolds, Malcolm, Xu, Yuanzhong, Doherty, Ryan, Collins, Eli, Meyer, Clemens, Rutherford, Eliza, Moreira, Erica, Ayoub, Kareem, Goel, Megha, Krawczyk, Jack, Du, Cosmo, Chi, Ed, Cheng, Heng-Tze, Ni, Eric, Shah, Purvi, Kane, Patrick, Chan, Betty, Faruqui, Manaal, Severyn, Aliaksei, Lin, Hanzhao, Li, YaGuang, Cheng, Yong, Ittycheriah, Abe, Mahdieh, Mahdis, Chen, Mia, Sun, Pei, Tran, Dustin, Bagri, Sumit, Lakshminarayanan, Balaji, Liu, Jeremiah, Orban, Andras, Güra, Fabian, Zhou, Hao, Song, Xinying, Boffy, Aurelien, Ganapathy, Harish, Zheng, Steven, Choe, HyunJeong, Weisz, Ágoston, Zhu, Tao, Lu, Yifeng, Gopal, Siddharth, Kahn, Jarrod, Kula, Maciej, Pitman, Jeff, Shah, Rushin, Taropa, Emanuel, Merey, Majd Al, Baeuml, Martin, Chen, Zhifeng, Shafey, Laurent El, Zhang, Yujing, Sercinoglu, Olcan, Tucker, George, Piqueras, Enrique, Krikun, Maxim, Barr, Iain, Savinov, Nikolay, Danihelka, Ivo, Roelofs, Becca, White, Anaïs, Andreassen, Anders, von Glehn, Tamara, Yagati, Lakshman, Kazemi, Mehran, Gonzalez, Lucas, Khalman, Misha, Sygnowski, Jakub, Frechette, Alexandre, Smith, Charlotte, Culp, Laura, Proleev, Lev, Luan, Yi, Chen, Xi, Lottes, James, Schucher, Nathan, Lebron, Federico, Rrustemi, Alban, Clay, Natalie, Crone, Phil, Kocisky, Tomas, Zhao, Jeffrey, Perz, Bartek, Yu, Dian, Howard, Heidi, Bloniarz, Adam, Rae, Jack W., Lu, Han, Sifre, Laurent, Maggioni, Marcello, Alcober, Fred, Garrette, Dan, Barnes, Megan, Thakoor, Shantanu, Austin, Jacob, Barth-Maron, Gabriel, Wong, William, Joshi, Rishabh, Chaabouni, Rahma, Fatiha, Deeni, Ahuja, Arun, Tomar, Gaurav Singh, Senter, Evan, Chadwick, Martin, Kornakov, Ilya, Attaluri, Nithya, Iturrate, Iñaki, Liu, Ruibo, Li, Yunxuan, Cogan, Sarah, Chen, Jeremy, Jia, Chao, Gu, Chenjie, Zhang, Qiao, Grimstad, Jordan, Hartman, Ale Jakse, Garcia, Xavier, Pillai, Thanumalayan Sankaranarayana, Devlin, Jacob, Laskin, Michael, Casas, Diego de Las, Valter, Dasha, Tao, Connie, Blanco, Lorenzo, Badia, Adrià Puigdomènech, Reitter, David, Chen, Mianna, Brennan, Jenny, Rivera, Clara, Brin, Sergey, Iqbal, Shariq, Surita, Gabriela, Labanowski, Jane, Rao, Abhi, Winkler, Stephanie, Parisotto, Emilio, Gu, Yiming, Olszewska, Kate, Addanki, Ravi, Miech, Antoine, Louis, Annie, Teplyashin, Denis, Brown, Geoff, Catt, Elliot, Balaguer, Jan, Xiang, Jackie, Wang, Pidong, Ashwood, Zoe, Briukhov, Anton, Webson, Albert, Ganapathy, Sanjay, Sanghavi, Smit, Kannan, Ajay, Chang, Ming-Wei, Stjerngren, Axel, Djolonga, Josip, Sun, Yuting, Bapna, Ankur, Aitchison, Matthew, Pejman, Pedram, Michalewski, Henryk, Yu, Tianhe, Wang, Cindy, Love, Juliette, Ahn, Junwhan, Bloxwich, Dawn, Han, Kehang, Humphreys, Peter, Sellam, Thibault, Bradbury, James, Godbole, Varun, Samangooei, Sina, Damoc, Bogdan, Kaskasoli, Alex, Arnold, Sébastien M. R., Vasudevan, Vijay, Agrawal, Shubham, Riesa, Jason, Lepikhin, Dmitry, Tanburn, Richard, Srinivasan, Srivatsan, Lim, Hyeontaek, Hodkinson, Sarah, Shyam, Pranav, Ferret, Johan, Hand, Steven, Garg, Ankush, Paine, Tom Le, Li, Jian, Li, Yujia, Giang, Minh, Neitz, Alexander, Abbas, Zaheer, York, Sarah, Reid, Machel, Cole, Elizabeth, Chowdhery, Aakanksha, Das, Dipanjan, Rogozińska, Dominika, Nikolaev, Vitaliy, Sprechmann, Pablo, Nado, Zachary, Zilka, Lukas, Prost, Flavien, He, Luheng, Monteiro, Marianne, Mishra, Gaurav, Welty, Chris, Newlan, Josh, Jia, Dawei, Allamanis, Miltiadis, Hu, Clara Huiyi, de Liedekerke, Raoul, Gilmer, Justin, Saroufim, Carl, Rijhwani, Shruti, Hou, Shaobo, Shrivastava, Disha, Baddepudi, Anirudh, Goldin, Alex, Ozturel, Adnan, Cassirer, Albin, Xu, Yunhan, Sohn, Daniel, Sachan, Devendra, Amplayo, Reinald Kim, Swanson, Craig, Petrova, Dessie, Narayan, Shashi, Guez, Arthur, Brahma, Siddhartha, Landon, Jessica, Patel, Miteyan, Zhao, Ruizhe, Villela, Kevin, Wang, Luyu, Jia, Wenhao, Rahtz, Matthew, Giménez, Mai, Yeung, Legg, Keeling, James, Georgiev, Petko, Mincu, Diana, Wu, Boxi, Haykal, Salem, Saputro, Rachel, Vodrahalli, Kiran, Qin, James, Cankara, Zeynep, Sharma, Abhanshu, Fernando, Nick, Hawkins, Will, Neyshabur, Behnam, Kim, Solomon, Hutter, Adrian, Agrawal, Priyanka, Castro-Ros, Alex, Driessche, George van den, Wang, Tao, Yang, Fan, Chang, Shuo-yiin, Komarek, Paul, McIlroy, Ross, Lučić, Mario, Zhang, Guodong, Farhan, Wael, Sharman, Michael, Natsev, Paul, Michel, Paul, Bansal, Yamini, Qiao, Siyuan, Cao, Kris, Shakeri, Siamak, Butterfield, Christina, Chung, Justin, Rubenstein, Paul Kishan, Agrawal, Shivani, Mensch, Arthur, Soparkar, Kedar, Lenc, Karel, Chung, Timothy, Pope, Aedan, Maggiore, Loren, Kay, Jackie, Jhakra, Priya, Wang, Shibo, Maynez, Joshua, Phuong, Mary, Tobin, Taylor, Tacchetti, Andrea, Trebacz, Maja, Robinson, Kevin, Katariya, Yash, Riedel, Sebastian, Bailey, Paige, Xiao, Kefan, Ghelani, Nimesh, Aroyo, Lora, Slone, Ambrose, Houlsby, Neil, Xiong, Xuehan, Yang, Zhen, Gribovskaya, Elena, Adler, Jonas, Wirth, Mateo, Lee, Lisa, Li, Music, Kagohara, Thais, Pavagadhi, Jay, Bridgers, Sophie, Bortsova, Anna, Ghemawat, Sanjay, Ahmed, Zafarali, Liu, Tianqi, Powell, Richard, Bolina, Vijay, Iinuma, Mariko, Zablotskaia, Polina, Besley, James, Chung, Da-Woon, Dozat, Timothy, Comanescu, Ramona, Si, Xiance, Greer, Jeremy, Su, Guolong, Polacek, Martin, Kaufman, Raphaël Lopez, Tokumine, Simon, Hu, Hexiang, Buchatskaya, Elena, Miao, Yingjie, Elhawaty, Mohamed, Siddhant, Aditya, Tomasev, Nenad, Xing, Jinwei, Greer, Christina, Miller, Helen, Ashraf, Shereen, Roy, Aurko, Zhang, Zizhao, Ma, Ada, Filos, Angelos, Besta, Milos, Blevins, Rory, Klimenko, Ted, Yeh, Chih-Kuan, Changpinyo, Soravit, Mu, Jiaqi, Chang, Oscar, Pajarskas, Mantas, Muir, Carrie, Cohen, Vered, Lan, Charline Le, Haridasan, Krishna, Marathe, Amit, Hansen, Steven, Douglas, Sholto, Samuel, Rajkumar, Wang, Mingqiu, Austin, Sophia, Lan, Chang, Jiang, Jiepu, Chiu, Justin, Lorenzo, Jaime Alonso, Sjösund, Lars Lowe, Cevey, Sébastien, Gleicher, Zach, Avrahami, Thi, Boral, Anudhyan, Srinivasan, Hansa, Selo, Vittorio, May, Rhys, Aisopos, Konstantinos, Hussenot, Léonard, Soares, Livio Baldini, Baumli, Kate, Chang, Michael B., Recasens, Adrià, Caine, Ben, Pritzel, Alexander, Pavetic, Filip, Pardo, Fabio, Gergely, Anita, Frye, Justin, Ramasesh, Vinay, Horgan, Dan, Badola, Kartikeya, Kassner, Nora, Roy, Subhrajit, Dyer, Ethan, Campos, Víctor Campos, Tomala, Alex, Tang, Yunhao, Badawy, Dalia El, White, Elspeth, Mustafa, Basil, Lang, Oran, Jindal, Abhishek, Vikram, Sharad, Gong, Zhitao, Caelles, Sergi, Hemsley, Ross, Thornton, Gregory, Feng, Fangxiaoyu, Stokowiec, Wojciech, Zheng, Ce, Thacker, Phoebe, Ünlü, Çağlar, Zhang, Zhishuai, Saleh, Mohammad, Svensson, James, Bileschi, Max, Patil, Piyush, Anand, Ankesh, Ring, Roman, Tsihlas, Katerina, Vezer, Arpi, Selvi, Marco, Shevlane, Toby, Rodriguez, Mikel, Kwiatkowski, Tom, Daruki, Samira, Rong, Keran, Dafoe, Allan, FitzGerald, Nicholas, Gu-Lemberg, Keren, Khan, Mina, Hendricks, Lisa Anne, Pellat, Marie, Feinberg, Vladimir, Cobon-Kerr, James, Sainath, Tara, Rauh, Maribeth, Hashemi, Sayed Hadi, Ives, Richard, Hasson, Yana, Noland, Eric, Cao, Yuan, Byrd, Nathan, Hou, Le, Wang, Qingze, Sottiaux, Thibault, Paganini, Michela, Lespiau, Jean-Baptiste, Moufarek, Alexandre, Hassan, Samer, Shivakumar, Kaushik, van Amersfoort, Joost, Mandhane, Amol, Joshi, Pratik, Goyal, Anirudh, Tung, Matthew, Brock, Andrew, Sheahan, Hannah, Misra, Vedant, Li, Cheng, Rakićević, Nemanja, Dehghani, Mostafa, Liu, Fangyu, Mittal, Sid, Oh, Junhyuk, Noury, Seb, Sezener, Eren, Huot, Fantine, Lamm, Matthew, De Cao, Nicola, Chen, Charlie, Mudgal, Sidharth, Stella, Romina, Brooks, Kevin, Vasudevan, Gautam, Liu, Chenxi, Chain, Mainak, Melinkeri, Nivedita, Cohen, Aaron, Wang, Venus, Seymore, Kristie, Zubkov, Sergey, Goel, Rahul, Yue, Summer, Krishnakumaran, Sai, Albert, Brian, Hurley, Nate, Sano, Motoki, Mohananey, Anhad, Joughin, Jonah, Filonov, Egor, Kępa, Tomasz, Eldawy, Yomna, Lim, Jiawern, Rishi, Rahul, Badiezadegan, Shirin, Bos, Taylor, Chang, Jerry, Jain, Sanil, Padmanabhan, Sri Gayatri Sundara, Puttagunta, Subha, Krishna, Kalpesh, Baker, Leslie, Kalb, Norbert, Bedapudi, Vamsi, Kurzrok, Adam, Lei, Shuntong, Yu, Anthony, Litvin, Oren, Zhou, Xiang, Wu, Zhichun, Sobell, Sam, Siciliano, Andrea, Papir, Alan, Neale, Robby, Bragagnolo, Jonas, Toor, Tej, Chen, Tina, Anklin, Valentin, Wang, Feiran, Feng, Richie, Gholami, Milad, Ling, Kevin, Liu, Lijuan, Walter, Jules, Moghaddam, Hamid, Kishore, Arun, Adamek, Jakub, Mercado, Tyler, Mallinson, Jonathan, Wandekar, Siddhinita, Cagle, Stephen, Ofek, Eran, Garrido, Guillermo, Lombriser, Clemens, Mukha, Maksim, Sun, Botu, Mohammad, Hafeezul Rahman, Matak, Josip, Qian, Yadi, Peswani, Vikas, Janus, Pawel, Yuan, Quan, Schelin, Leif, David, Oana, Garg, Ankur, He, Yifan, Duzhyi, Oleksii, Älgmyr, Anton, Lottaz, Timothée, Li, Qi, Yadav, Vikas, Xu, Luyao, Chinien, Alex, Shivanna, Rakesh, Chuklin, Aleksandr, Li, Josie, Spadine, Carrie, Wolfe, Travis, Mohamed, Kareem, Das, Subhabrata, Dai, Zihang, He, Kyle, von Dincklage, Daniel, Upadhyay, Shyam, Maurya, Akanksha, Chi, Luyan, Krause, Sebastian, Salama, Khalid, Rabinovitch, Pam G, M, Pavan Kumar Reddy, Selvan, Aarush, Dektiarev, Mikhail, Ghiasi, Golnaz, Guven, Erdem, Gupta, Himanshu, Liu, Boyi, Sharma, Deepak, Shtacher, Idan Heimlich, Paul, Shachi, Akerlund, Oscar, Aubet, François-Xavier, Huang, Terry, Zhu, Chen, Zhu, Eric, Teixeira, Elico, Fritze, Matthew, Bertolini, Francesco, Marinescu, Liana-Eleonora, Bölle, Martin, Paulus, Dominik, Gupta, Khyatti, Latkar, Tejasi, Chang, Max, Sanders, Jason, Wilson, Roopa, Wu, Xuewei, Tan, Yi-Xuan, Thiet, Lam Nguyen, Doshi, Tulsee, Lall, Sid, Mishra, Swaroop, Chen, Wanming, Luong, Thang, Benjamin, Seth, Lee, Jasmine, Andrejczuk, Ewa, Rabiej, Dominik, Ranjan, Vipul, Styrc, Krzysztof, Yin, Pengcheng, Simon, Jon, Harriott, Malcolm Rose, Bansal, Mudit, Robsky, Alexei, Bacon, Geoff, Greene, David, Mirylenka, Daniil, Zhou, Chen, Sarvana, Obaid, Goyal, Abhimanyu, Andermatt, Samuel, Siegler, Patrick, Horn, Ben, Israel, Assaf, Pongetti, Francesco, Chen, Chih-Wei "Louis", Selvatici, Marco, Silva, Pedro, Wang, Kathie, Tolins, Jackson, Guu, Kelvin, Yogev, Roey, Cai, Xiaochen, Agostini, Alessandro, Shah, Maulik, Nguyen, Hung, Donnaile, Noah Ó, Pereira, Sébastien, Friso, Linda, Stambler, Adam, Kuang, Chenkai, Romanikhin, Yan, Geller, Mark, Yan, ZJ, Jang, Kane, Lee, Cheng-Chun, Fica, Wojciech, Malmi, Eric, Tan, Qijun, Banica, Dan, Balle, Daniel, Pham, Ryan, Huang, Yanping, Avram, Diana, Shi, Hongzhi, Singh, Jasjot, Hidey, Chris, Ahuja, Niharika, Saxena, Pranab, Dooley, Dan, Potharaju, Srividya Pranavi, O'Neill, Eileen, Gokulchandran, Anand, Foley, Ryan, Zhao, Kai, Dusenberry, Mike, Liu, Yuan, Mehta, Pulkit, Kotikalapudi, Ragha, Safranek-Shrader, Chalence, Goodman, Andrew, Kessinger, Joshua, Globen, Eran, Kolhar, Prateek, Gorgolewski, Chris, Ibrahim, Ali, Song, Yang, Eichenbaum, Ali, Brovelli, Thomas, Potluri, Sahitya, Lahoti, Preethi, Baetu, Cip, Ghorbani, Ali, Chen, Charles, Crawford, Andy, Pal, Shalini, Sridhar, Mukund, Gurita, Petru, Mujika, Asier, Petrovski, Igor, Cedoz, Pierre-Louis, Li, Chenmei, Chen, Shiyuan, Santo, Niccolò Dal, Goyal, Siddharth, Punjabi, Jitesh, Kappaganthu, Karthik, Kwak, Chester, LV, Pallavi, Velury, Sarmishta, Choudhury, Himadri, Hall, Jamie, Shah, Premal, Figueira, Ricardo, Thomas, Matt, Lu, Minjie, Zhou, Ting, Kumar, Chintu, Jurdi, Thomas, Chikkerur, Sharat, Ma, Yenai, Yu, Adams, Kwak, Soo, Ähdel, Victor, Rajayogam, Sujeevan, Choma, Travis, Liu, Fei, Barua, Aditya, Ji, Colin, Park, Ji Ho, Hellendoorn, Vincent, Bailey, Alex, Bilal, Taylan, Zhou, Huanjie, Khatir, Mehrdad, Sutton, Charles, Rzadkowski, Wojciech, Macintosh, Fiona, Shagin, Konstantin, Medina, Paul, Liang, Chen, Zhou, Jinjing, Shah, Pararth, Bi, Yingying, Dankovics, Attila, Banga, Shipra, Lehmann, Sabine, Bredesen, Marissa, Lin, Zifan, Hoffmann, John Eric, Lai, Jonathan, Chung, Raynald, Yang, Kai, Balani, Nihal, Bražinskas, Arthur, Sozanschi, Andrei, Hayes, Matthew, Alcalde, Héctor Fernández, Makarov, Peter, Chen, Will, Stella, Antonio, Snijders, Liselotte, Mandl, Michael, Kärrman, Ante, Nowak, Paweł, Wu, Xinyi, Dyck, Alex, Vaidyanathan, Krishnan, R, Raghavender, Mallet, Jessica, Rudominer, Mitch, Johnston, Eric, Mittal, Sushil, Udathu, Akhil, Christensen, Janara, Verma, Vishal, Irving, Zach, Santucci, Andreas, Elsayed, Gamaleldin, Davoodi, Elnaz, Georgiev, Marin, Tenney, Ian, Hua, Nan, Cideron, Geoffrey, Leurent, Edouard, Alnahlawi, Mahmoud, Georgescu, Ionut, Wei, Nan, Zheng, Ivy, Scandinaro, Dylan, Jiang, Heinrich, Snoek, Jasper, Sundararajan, Mukund, Wang, Xuezhi, Ontiveros, Zack, Karo, Itay, Cole, Jeremy, Rajashekhar, Vinu, Tumeh, Lara, Ben-David, Eyal, Jain, Rishub, Uesato, Jonathan, Datta, Romina, Bunyan, Oskar, Wu, Shimu, Zhang, John, Stanczyk, Piotr, Zhang, Ye, Steiner, David, Naskar, Subhajit, Azzam, Michael, Johnson, Matthew, Paszke, Adam, Chiu, Chung-Cheng, Elias, Jaume Sanchez, Mohiuddin, Afroz, Muhammad, Faizan, Miao, Jin, Lee, Andrew, Vieillard, Nino, Park, Jane, Zhang, Jiageng, Stanway, Jeff, Garmon, Drew, Karmarkar, Abhijit, Dong, Zhe, Lee, Jong, Kumar, Aviral, Zhou, Luowei, Evens, Jonathan, Isaac, William, Irving, Geoffrey, Loper, Edward, Fink, Michael, Arkatkar, Isha, Chen, Nanxin, Shafran, Izhak, Petrychenko, Ivan, Chen, Zhe, Jia, Johnson, Levskaya, Anselm, Zhu, Zhenkai, Grabowski, Peter, Mao, Yu, Magni, Alberto, Yao, Kaisheng, Snaider, Javier, Casagrande, Norman, Palmer, Evan, Suganthan, Paul, Castaño, Alfonso, Giannoumis, Irene, Kim, Wooyeol, Rybiński, Mikołaj, Sreevatsa, Ashwin, Prendki, Jennifer, Soergel, David, Goedeckemeyer, Adrian, Gierke, Willi, Jafari, Mohsen, Gaba, Meenu, Wiesner, Jeremy, Wright, Diana Gage, Wei, Yawen, Vashisht, Harsha, Kulizhskaya, Yana, Hoover, Jay, Le, Maigo, Li, Lu, Iwuanyanwu, Chimezie, Liu, Lu, Ramirez, Kevin, Khorlin, Andrey, Cui, Albert, LIN, Tian, Wu, Marcus, Aguilar, Ricardo, Pallo, Keith, Chakladar, Abhishek, Perng, Ginger, Abellan, Elena Allica, Zhang, Mingyang, Dasgupta, Ishita, Kushman, Nate, Penchev, Ivo, Repina, Alena, Wu, Xihui, van der Weide, Tom, Ponnapalli, Priya, Kaplan, Caroline, Simsa, Jiri, Li, Shuangfeng, Dousse, Olivier, Piper, Jeff, Ie, Nathan, Pasumarthi, Rama, Lintz, Nathan, Vijayakumar, Anitha, Andor, Daniel, Valenzuela, Pedro, Lui, Minnie, Paduraru, Cosmin, Peng, Daiyi, Lee, Katherine, Zhang, Shuyuan, Greene, Somer, Nguyen, Duc Dung, Kurylowicz, Paula, Hardin, Cassidy, Dixon, Lucas, Janzer, Lili, Choo, Kiam, Feng, Ziqiang, Zhang, Biao, Singhal, Achintya, Du, Dayou, McKinnon, Dan, Antropova, Natasha, Bolukbasi, Tolga, Keller, Orgad, Reid, David, Finchelstein, Daniel, Raad, Maria Abi, Crocker, Remi, Hawkins, Peter, Dadashi, Robert, Gaffney, Colin, Franko, Ken, Bulanova, Anna, Leblond, Rémi, Chung, Shirley, Askham, Harry, Cobo, Luis C., Xu, Kelvin, Fischer, Felix, Xu, Jun, Sorokin, Christina, Alberti, Chris, Lin, Chu-Cheng, Evans, Colin, Dimitriev, Alek, Forbes, Hannah, Banarse, Dylan, Tung, Zora, Omernick, Mark, Bishop, Colton, Sterneck, Rachel, Jain, Rohan, Xia, Jiawei, Amid, Ehsan, Piccinno, Francesco, Wang, Xingyu, Banzal, Praseem, Mankowitz, Daniel J., Polozov, Alex, Krakovna, Victoria, Brown, Sasha, Bateni, MohammadHossein, Duan, Dennis, Firoiu, Vlad, Thotakuri, Meghana, Natan, Tom, Geist, Matthieu, Girgin, Ser tan, Li, Hui, Ye, Jiayu, Roval, Ofir, Tojo, Reiko, Kwong, Michael, Lee-Thorp, James, Yew, Christopher, Sinopalnikov, Danila, Ramos, Sabela, Mellor, John, Sharma, Abhishek, Wu, Kathy, Miller, David, Sonnerat, Nicolas, Vnukov, Denis, Greig, Rory, Beattie, Jennifer, Caveness, Emily, Bai, Libin, Eisenschlos, Julian, Korchemniy, Alex, Tsai, Tomy, Jasarevic, Mimi, Kong, Weize, Dao, Phuong, Zheng, Zeyu, Liu, Frederick, Zhu, Rui, Teh, Tian Huey, Sanmiya, Jason, Gladchenko, Evgeny, Trdin, Nejc, Toyama, Daniel, Rosen, Evan, Tavakkol, Sasan, Xue, Linting, Elkind, Chen, Woodman, Oliver, Carpenter, John, Papamakarios, George, Kemp, Rupert, Kafle, Sushant, Grunina, Tanya, Sinha, Rishika, Talbert, Alice, Wu, Diane, Owusu-Afriyie, Denese, Thornton, Chloe, Pont-Tuset, Jordi, Narayana, Pradyumna, Li, Jing, Fatehi, Saaber, Wieting, John, Ajmeri, Omar, Uria, Benigno, Ko, Yeongil, Knight, Laura, Héliou, Amélie, Niu, Ning, Gu, Shane, Pang, Chenxi, Li, Yeqing, Levine, Nir, Stolovich, Ariel, Santamaria-Fernandez, Rebeca, Goenka, Sonam, Yustalim, Wenny, Strudel, Robin, Elqursh, Ali, Deck, Charlie, Lee, Hyo, Li, Zonglin, Levin, Kyle, Hoffmann, Raphael, Holtmann-Rice, Dan, Bachem, Olivier, Arora, Sho, Koh, Christy, Yeganeh, Soheil Hassas, Põder, Siim, Tariq, Mukarram, Sun, Yanhua, Ionita, Lucian, Seyedhosseini, Mojtaba, Tafti, Pouya, Liu, Zhiyu, Gulati, Anmol, Liu, Jasmine, Ye, Xinyu, Chrzaszcz, Bart, Wang, Lily, Sethi, Nikhil, Li, Tianrun, Brown, Ben, Singh, Shreya, Fan, Wei, Parisi, Aaron, Stanton, Joe, Koverkathu, Vinod, Choquette-Choo, Christopher A., Li, Yunjie, Lu, TJ, Shroff, Prakash, Varadarajan, Mani, Bahargam, Sanaz, Willoughby, Rob, Gaddy, David, Desjardins, Guillaume, Cornero, Marco, Robenek, Brona, Mittal, Bhavishya, Albrecht, Ben, Shenoy, Ashish, Moiseev, Fedor, Jacobsson, Henrik, Ghaffarkhah, Alireza, Rivière, Morgane, Walton, Alanna, Crepy, Clément, Parrish, Alicia, Zhou, Zongwei, Farabet, Clement, Radebaugh, Carey, Srinivasan, Praveen, van der Salm, Claudia, Fidjeland, Andreas, Scellato, Salvatore, Latorre-Chimoto, Eri, Klimczak-Plucińska, Hanna, Bridson, David, de Cesare, Dario, Hudson, Tom, Mendolicchio, Piermaria, Walker, Lexi, Morris, Alex, Mauger, Matthew, Guseynov, Alexey, Reid, Alison, Odoom, Seth, Loher, Lucia, Cotruta, Victor, Yenugula, Madhavi, Grewe, Dominik, Petrushkina, Anastasia, Duerig, Tom, Sanchez, Antonio, Yadlowsky, Steve, Shen, Amy, Globerson, Amir, Webb, Lynette, Dua, Sahil, Li, Dong, Bhupatiraju, Surya, Hurt, Dan, Qureshi, Haroon, Agarwal, Ananth, Shani, Tomer, Eyal, Matan, Khare, Anuj, Belle, Shreyas Rammohan, Wang, Lei, Tekur, Chetan, Kale, Mihir Sanjay, Wei, Jinliang, Sang, Ruoxin, Saeta, Brennan, Liechty, Tyler, Sun, Yi, Zhao, Yao, Lee, Stephan, Nayak, Pandu, Fritz, Doug, Vuyyuru, Manish Reddy, Aslanides, John, Vyas, Nidhi, Wicke, Martin, Ma, Xiao, Eltyshev, Evgenii, Martin, Nina, Cate, Hardie, Manyika, James, Amiri, Keyvan, Kim, Yelin, Xiong, Xi, Kang, Kai, Luisier, Florian, Tripuraneni, Nilesh, Madras, David, Guo, Mandy, Waters, Austin, Wang, Oliver, Ainslie, Joshua, Baldridge, Jason, Zhang, Han, Pruthi, Garima, Bauer, Jakob, Yang, Feng, Mansour, Riham, Gelman, Jason, Xu, Yang, Polovets, George, Liu, Ji, Cai, Honglong, Chen, Warren, Sheng, XiangHai, Xue, Emily, Ozair, Sherjil, Angermueller, Christof, Li, Xiaowei, Sinha, Anoop, Wang, Weiren, Wiesinger, Julia, Koukoumidis, Emmanouil, Tian, Yuan, Iyer, Anand, Gurumurthy, Madhu, Goldenson, Mark, Shah, Parashar, Blake, MK, Yu, Hongkun, Urbanowicz, Anthony, Palomaki, Jennimaria, Fernando, Chrisantha, Durden, Ken, Mehta, Harsh, Momchev, Nikola, Rahimtoroghi, Elahe, Georgaki, Maria, Raul, Amit, Ruder, Sebastian, Redshaw, Morgan, Lee, Jinhyuk, Zhou, Denny, Jalan, Komal, Li, Dinghua, Hechtman, Blake, Schuh, Parker, Nasr, Milad, Milan, Kieran, Mikulik, Vladimir, Franco, Juliana, Green, Tim, Nguyen, Nam, Kelley, Joe, Mahendru, Aroma, Hu, Andrea, Howland, Joshua, Vargas, Ben, Hui, Jeffrey, Bansal, Kshitij, Rao, Vikram, Ghiya, Rakesh, Wang, Emma, Ye, Ke, Sarr, Jean Michel, Preston, Melanie Moranski, Elish, Madeleine, Li, Steve, Kaku, Aakash, Gupta, Jigar, Pasupat, Ice, Juan, Da-Cheng, Someswar, Milan, M., Tejvi, Chen, Xinyun, Amini, Aida, Fabrikant, Alex, Chu, Eric, Dong, Xuanyi, Muthal, Amruta, Buthpitiya, Senaka, Jauhari, Sarthak, Khandelwal, Urvashi, Hitron, Ayal, Ren, Jie, Rinaldi, Larissa, Drath, Shahar, Dabush, Avigail, Jiang, Nan-Jiang, Godhia, Harshal, Sachs, Uli, Chen, Anthony, Fan, Yicheng, Taitelbaum, Hagai, Noga, Hila, Dai, Zhuyun, Wang, James, Hamer, Jenny, Ferng, Chun-Sung, Elkind, Chenel, Atias, Aviel, Lee, Paulina, Listík, Vít, Carlen, Mathias, van de Kerkhof, Jan, Pikus, Marcin, Zaher, Krunoslav, Müller, Paul, Zykova, Sasha, Stefanec, Richard, Gatsko, Vitaly, Hirnschall, Christoph, Sethi, Ashwin, Xu, Xingyu Federico, Ahuja, Chetan, Tsai, Beth, Stefanoiu, Anca, Feng, Bo, Dhandhania, Keshav, Katyal, Manish, Gupta, Akshay, Parulekar, Atharva, Pitta, Divya, Zhao, Jing, Bhatia, Vivaan, Bhavnani, Yashodha, Alhadlaq, Omar, Li, Xiaolin, Danenberg, Peter, Tu, Dennis, Pine, Alex, Filippova, Vera, Ghosh, Abhipso, Limonchik, Ben, Urala, Bhargava, Lanka, Chaitanya Krishna, Clive, Derik, Li, Edward, Wu, Hao, Hongtongsak, Kevin, Li, Ianna, Thakkar, Kalind, Omarov, Kuanysh, Majmundar, Kushal, Alverson, Michael, Kucharski, Michael, Patel, Mohak, Jain, Mudit, Zabelin, Maksim, Pelagatti, Paolo, Kohli, Rohan, Kumar, Saurabh, Kim, Joseph, Sankar, Swetha, Shah, Vineet, Ramachandruni, Lakshmi, Zeng, Xiangkai, Bariach, Ben, Weidinger, Laura, Vu, Tu, Andreev, Alek, He, Antoine, Hui, Kevin, Kashem, Sheleem, Subramanya, Amar, Hsiao, Sissie, Hassabis, Demis, Kavukcuoglu, Koray, Sadovsky, Adam, Le, Quoc, Strohman, Trevor, Wu, Yonghui, Petrov, Slav, Dean, Jeffrey, and Vinyals, Oriol

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Computer Vision and Pattern Recognition
Abstract

This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consists of Ultra, Pro, and Nano sizes, suitable for applications ranging from complex reasoning tasks to on-device memory-constrained use-cases. Evaluation on a broad range of benchmarks shows that our most-capable Gemini Ultra model advances the state of the art in 30 of 32 of these benchmarks - notably being the first model to achieve human-expert performance on the well-studied exam benchmark MMLU, and improving the state of the art in every one of the 20 multimodal benchmarks we examined. We believe that the new capabilities of the Gemini family in cross-modal reasoning and language understanding will enable a wide variety of use cases. We discuss our approach toward post-training and deploying Gemini models responsibly to users through services including Gemini, Gemini Advanced, Google AI Studio, and Cloud Vertex AI.

Published
2023

4. NOTIFICAÇÃO DE CASOS DE MENINGITE EM TERESINA, PI EM 2022

Author

ROCHA STANCZYK, VIVIANNE, primary, TAILENA REINISCH, IOHANA, additional, NOGUEIRA DE OLIVEIRA, AMAURY, additional, EVANDRO DE SOUZA LIMA, MARCOS, additional, SATORU OHASHI, GABRIEL, additional, CRISTINA PEREIRA FRANCO, BRUNA, additional, DE SOUSA MATOS, VILIAN, additional, ALBERTO DUARTE GOMES BATISTA, JOSÉ, additional, MARIA RODRIGUES LOPES, ANÁLIA, additional, SINARA COSTA DE ASSUNÇÃO, MARIA, additional, APARECIDA SOARES MACÊDO, THAUANE, additional, RAYANE FERREIRA DA SILVA, ALICE, additional, VALÉRIA SOUSA DA SILVA, ANA, additional, SILVA DE AGUIAR FILHO, HILDO, additional, LIMA SANTOS, JHULIANA, additional, and DA SILVA OLIVEIRA, KEICIELE, additional

Published
2024
Full Text
View/download PDF

5. PRINCIPAIS DOENÇAS DE CARÁTER ZOONÓTICAS NEGLIGENCIADAS NO BRASIL DE IMPORTÂNCIA MÉDICA VETERINÁRIA

Author

ROCHA STANCZYK, VIVIANNE, primary, BEATRIZ SOUSA COSTA, ANA, additional, SATORU OHASHI, GABRIEL, additional, NOGUEIRA DE OLIVEIRA, AMAURY, additional, EVANDRO DE SOUZA LIMA, MARCOS, additional, MARIA ALVES DO NASCIMENTO, IZIANNE, additional, SOUSA DE MATOS, VILIAN, additional, ALBERTO DUARTE GOMES BATISTA, JOSÉ, additional, CRISTINA PEREIRA FRANCO, BRUNA, additional, PRISCILLA MENDES DE SOUZA, ALDAYNNY, additional, VICTÓRIA SANTOS DE SOUZA, JÚLIA, additional, LIMA NOGUEIRA, SAMILY, additional, FLORENCIO DA CRUZ, ALINE, additional, SOUZA SILVA, ALESSON, additional, MUNIZ DA COSTA, ANTONIO, additional, and DE OLIVEIRA, SABRINA, additional

Published
2024
Full Text
View/download PDF

6. PRINCIPAIS ACIDENTES COM ANIMAIS PEÇONHENTOS DE INTERESSE PARA A SAÚDE PÚBLICA NO BRASIL

Author

ROCHA STANCZYK, VIVIANNE, primary, BEATRIZ SOUSA COSTA, ANA, additional, EVANDRO DE SOUZA LIMA, MARCOS, additional, CLAYVER BENVINDO RIBEIRO, IGOR, additional, NOGUEIRA DE OLIVEIRA, AMAURY, additional, CRISTINA PEREIRA FRANCO, BRUNA, additional, DA SILVA OLIVEIRA, KEICIELE, additional, CARVALHO DA SILVEIRA, CHARLES, additional, ALVES COUTINHO, ANUSKA, additional, CAROLINE LEAL DE ARAÚJO, NAYANA, additional, TEIXEIRA DE CASTRO, LUCAS, additional, SANTOS E SILVA, GABRIELA, additional, ALICE DA SILVA, LÍVIA, additional, BORGES DINIZ, JÚLIA, additional, LUCENA CORDEIRO, MICAELA, additional, and MONTEIRO MAGALHÃES CRUZ, MARIANA, additional

Published
2024
Full Text
View/download PDF

7. On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes

Author

Agarwal, Rishabh, Vieillard, Nino, Zhou, Yongchao, Stanczyk, Piotr, Ramos, Sabela, Geist, Matthieu, and Bachem, Olivier

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computation and Language
Abstract

Knowledge distillation (KD) is widely used for compressing a teacher model to reduce its inference cost and memory footprint, by training a smaller student model. However, current KD methods for auto-regressive sequence models suffer from distribution mismatch between output sequences seen during training and those generated by the student during inference. To address this issue, we introduce Generalized Knowledge Distillation (GKD). Instead of solely relying on a fixed set of output sequences, GKD trains the student on its self-generated output sequences by leveraging feedback from the teacher on such sequences. Unlike supervised KD approaches, GKD also offers the flexibility to employ alternative loss functions between the student and teacher, which can be useful when the student lacks the expressivity to mimic the teacher's distribution. Furthermore, GKD facilitates the seamless integration of distillation with RL fine-tuning (RLHF). We demonstrate the efficacy of GKD for distilling auto-regressive language models on summarization, translation, and arithmetic reasoning tasks, and task-agnostic distillation for instruction-tuning., Comment: Accepted at ICLR 2024. First two authors contributed equally

Published
2023

8. Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback

Author

Roit, Paul, Ferret, Johan, Shani, Lior, Aharoni, Roee, Cideron, Geoffrey, Dadashi, Robert, Geist, Matthieu, Girgin, Sertan, Hussenot, Léonard, Keller, Orgad, Momchev, Nikola, Ramos, Sabela, Stanczyk, Piotr, Vieillard, Nino, Bachem, Olivier, Elidan, Gal, Hassidim, Avinatan, Pietquin, Olivier, and Szpektor, Idan

Subjects
Computer Science - Computation and Language
Abstract

Despite the seeming success of contemporary grounded text generation systems, they often tend to generate factually inconsistent text with respect to their input. This phenomenon is emphasized in tasks like summarization, in which the generated summaries should be corroborated by their source article. In this work, we leverage recent progress on textual entailment models to directly address this problem for abstractive summarization systems. We use reinforcement learning with reference-free, textual entailment rewards to optimize for factual consistency and explore the ensuing trade-offs, as improved consistency may come at the cost of less informative or more extractive summaries. Our results, according to both automatic metrics and human evaluation, show that our method considerably improves the faithfulness, salience, and conciseness of the generated summaries., Comment: ACL 2023

Published
2023

9. Enriched Discretisation: Information Fusion from Supervised and Unsupervised Processing

Author

Stańczyk, Urszula, Zielosko, Beata, Baron, Grzegorz, Spagnoletti, Paolo, Series Editor, De Marco, Marco, Series Editor, Pouloudi, Nancy, Series Editor, Te'eni, Dov, Series Editor, vom Brocke, Jan, Series Editor, Winter, Robert, Series Editor, Baskerville, Richard, Series Editor, Za, Stefano, Series Editor, Braccini, Alessio Maria, Series Editor, Rodrigues da Silva, Alberto, editor, Mira da Silva, Miguel, editor, Estima, Jacinto, editor, Barry, Chris, editor, Lang, Michael, editor, Linger, Henry, editor, and Schneider, Christoph, editor

Published
2024
Full Text
View/download PDF

11. Genetic influence on vascular smooth muscle cell apoptosis

Author

David G. McVey, Catherine Andreadi, Peng Gong, Paulina J. Stanczyk, Charles U. Solomon, Lenka Turner, Liu Yan, Runji Chen, Junjun Cao, Christopher P. Nelson, John R. Thompson, Haojie Yu, Tom R. Webb, Nilesh J. Samani, and Shu Ye

Subjects
Cytology, QH573-671
Abstract

Abstract Vascular smooth muscle cell (VSMC) proliferation, migration, and apoptosis play important roles in many physiological processes and pathological conditions. To identify genetic influences on VSMC behavior, we measured these traits and undertook genome-wide association studies in primary umbilical artery-derived VSMCs from >2000 individuals. Although there were no genome-wide significant associations for VSMC proliferation or migration, genetic variants at two genomic loci (7p15.3 and 7q32.3) showed highly significant associations with VSMC apoptosis (P = 1.95 × 10−13 and P = 7.47 × 10−9, respectively). The lead variant at the 7p51.3 locus was associated with increased expression of the GSDME and PALS2 genes in VSMCs. Knockdown of GSDME or PALS2 in VSMCs attenuated apoptotic cell death. A protein co-immunoprecipitation assay indicated that GSDME complexed with PALS2. PALS2 knockdown attenuated activated caspase-3 and GSDME fragmentation, whilst GSDME knockdown also reduced activated caspase-3. These findings provide new insights into the genetic regulation of VSMC apoptosis, with potential utility for therapeutic development.

Published
2024
Full Text
View/download PDF

14. Aperiodic activity differences in individuals with high and low temporal processing efficiency

Author

Klaudia Krystecka, Magdalena Stanczyk, Mikolaj Magnuski, Elzbieta Szelag, and Aneta Szymaszek

Subjects
Temporal information processing, Electroencephalography, Aperiodic activity, Resting state, Gamma oscillations, Cognition, Neurosciences. Biological psychiatry. Neuropsychiatry, RC321-571
Abstract

It is known that Temporal Information Processing (TIP) underpins our cognitive functioning. Previous research has focused on the relationship between TIP efficiency and oscillatory brain activity, especially the gamma rhythm; however, non-oscillatory (aperiodic or 1/f) brain activity has often been missed. Recent studies have identified the 1/f component as being important for the functioning of the brain. Therefore, the current study aimed to verify whether TIP efficiency is associated with specific EEG resting state cortical activity patterns, including oscillatory and non-oscillatory (aperiodic) brain activities. To measure individual TIP efficiency, we used two behavioral tasks in which the participant judges the order of two sounds separated by millisecond intervals. Based on the above procedure, participants were classified into two groups with high and low TIP efficiency. Using cluster-based permutation analyses, we examined between-group differences in oscillatory and non-oscillatory (aperiodic) components across the 1–90 Hz range. The results revealed that the groups differed in the aperiodic component across the 30–80 Hz range in fronto-central topography. In other words, participants with low TIP efficiency exhibited higher levels of aperiodic activity, and thus a flatter frequency spectrum compared to those with high TIP efficiency. We conclude that participants with low TIP efficiency display higher levels of ‘neural noise’, which is associated with poorer quality and speed of neural processing.

Published
2024
Full Text
View/download PDF

20. Neuroendocrine, neurotransmitter, and gut microbiota imbalance contributing to potential psychiatric disorder prevalence in polycystic ovarian syndrome

Author

Karis I. Sarkisian, Lananh Ho, B.S., Jane Yang, B.A., Rachel Mandelbaum, M.D., and Frank Z. Stanczyk, Ph.D.

Subjects
Gut-brain axis, neuroendocrine effects, neurotransmitter effects, polycystic ovarian syndrome, psychiatric disorders, Diseases of the genitourinary system. Urology, RC870-923, Gynecology and obstetrics, RG1-991
Abstract

Polycystic ovarian syndrome (PCOS) is the most common endocrine disorder in women, affecting up to 15% of reproductive-aged women. Polycystic ovarian syndrome is a heterogeneous disorder, both in the sense that many different factors may play a role in its manifestation and that multiple systems throughout the body can be affected. Polycystic ovarian syndrome has been linked to an increased prevalence of various psychiatric disorders, including depression and anxiety. Despite the socioeconomic effect that these disorders may have on patients with PCOS and society as a whole, this association is largely lacking in research. There are currently several theories regarding the link between PCOS and mental health. Some suggest that the overactive hypothalamic-pituitary-ovarian and hypothalamic-pituitary-adrenal axes in PCOS patients may alter the hormonal profile and contribute to the development of psychiatric disorders. Other studies speculate that abnormal levels of neurotransmitters and neuronal signaling may play a role. Recently, more research has begun to focus on the gut-brain axis, addressing the nutritional needs of PCOS patients. Studies show that dietary factors such as probiotics and micronutrient supplementation may significantly improve psychiatric symptoms in PCOS patients while helping regulate neurotransmitter levels in the body. In this review, we examine different theories regarding the association between PCOS and psychiatric disorders and point out different areas of research that are needed to broaden our understanding of this association.

Published
2023
Full Text
View/download PDF

21. A common timing mechanism across different millisecond domains: evidence from perceptual and motor tasks

Author

Magdalena Stanczyk, Elzbieta Szelag, Klaudia Krystecka, and Aneta Szymaszek

Subjects
Medicine, Science
Abstract

Abstract Temporal information processing (TIP) constitutes a complex construct that underlies many cognitive functions and operates in a few hierarchically ordered time domains. This study aimed to verify the relationship between the tens of milliseconds and hundreds of milliseconds domains, referring to perceptual and motor timing, respectively. Sixty four young healthy individuals participated in this study. They underwent two auditory temporal order judgement tasks to assess their performance in the tens of milliseconds domain; on this basis, groups of high-level performers (HLP) and low-level performers (LLP) were identified. Then, a maximum tapping task was used to evaluate performance in the hundreds of milliseconds domain. The most remarkable result was that HLP achieved a faster tapping rate and synchronised quicker with their “internal clock” during the tapping task than did LLP. This result shows that there is a relationship between accuracy in judging temporally asynchronous stimuli and ability to achieve and maintain the pace of a movement adequate to one’s internal pacemaker. This could indicate the strong contribution of a common timing mechanism, responsible for temporal organisation and coordination of behaviours across different millisecond domains.

Published
2023
Full Text
View/download PDF

22. RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learning

Author

Ramos, Sabela, Girgin, Sertan, Hussenot, Léonard, Vincent, Damien, Yakubovich, Hanna, Toyama, Daniel, Gergely, Anita, Stanczyk, Piotr, Marinier, Raphael, Harmsen, Jeremiah, Pietquin, Olivier, and Momchev, Nikola

Subjects
Computer Science - Machine Learning
Abstract

We introduce RLDS (Reinforcement Learning Datasets), an ecosystem for recording, replaying, manipulating, annotating and sharing data in the context of Sequential Decision Making (SDM) including Reinforcement Learning (RL), Learning from Demonstrations, Offline RL or Imitation Learning. RLDS enables not only reproducibility of existing research and easy generation of new datasets, but also accelerates novel research. By providing a standard and lossless format of datasets it enables to quickly test new algorithms on a wider range of tasks. The RLDS ecosystem makes it easy to share datasets without any loss of information and to be agnostic to the underlying original format when applying various data processing pipelines to large collections of datasets. Besides, RLDS provides tools for collecting data generated by either synthetic agents or humans, as well as for inspecting and manipulating the collected data. Ultimately, integration with TFDS facilitates the sharing of RL datasets with the research community., Comment: https://github.com/google-research/rlds

Published
2021

24. BOND: Aligning LLMs with Best-of-N Distillation.

Author

Pier Giuseppe Sessa, Robert Dadashi, Léonard Hussenot, Johan Ferret, Nino Vieillard, Alexandre Ramé, Bobak Shahriari, Sarah Perrin, Abe Friesen, Geoffrey Cideron, Sertan Girgin, Piotr Stanczyk, Andrea Michi, Danila Sinopalnikov, Sabela Ramos, Amélie Héliou, Aliaksei Severyn, Matt Hoffman 0001, Nikola Momchev, and Olivier Bachem

Published
2024
Full Text
View/download PDF

30. Elucidating mechanisms of genetic cross-disease associations at the PROCR vascular disease locus

Author

Stacey, David, Chen, Lingyan, Stanczyk, Paulina J, Howson, Joanna MM, Mason, Amy M, Burgess, Stephen, MacDonald, Stephen, Langdown, Jonathan, McKinney, Harriett, Downes, Kate, Farahi, Neda, Peters, James E, Basu, Saonli, Pankow, James S, Tang, Weihong, Pankratz, Nathan, Sabater-Lleal, Maria, de Vries, Paul S, Smith, Nicholas L, Gelinas, Amy D, Schneider, Daniel J, Janjic, Nebojsa, Samani, Nilesh J, Ye, Shu, Summers, Charlotte, Chilvers, Edwin R, Danesh, John, and Paul, Dirk S

Subjects
Biological Sciences, Genetics, Prevention, Cardiovascular, Atherosclerosis, Hematology, Heart Disease - Coronary Heart Disease, Heart Disease, Aetiology, 2.1 Biological and endogenous factors, Inflammatory and immune system, Antigens, CD, Crosses, Genetic, Endothelial Cells, Endothelial Protein C Receptor, Humans, Protein C, Receptors, Cell Surface, Thrombosis, Venous Thromboembolism, CHARGE Hemostasis Working Group
Abstract

Many individual genetic risk loci have been associated with multiple common human diseases. However, the molecular basis of this pleiotropy often remains unclear. We present an integrative approach to reveal the molecular mechanism underlying the PROCR locus, associated with lower coronary artery disease (CAD) risk but higher venous thromboembolism (VTE) risk. We identify PROCR-p.Ser219Gly as the likely causal variant at the locus and protein C as a causal factor. Using genetic analyses, human recall-by-genotype and in vitro experimentation, we demonstrate that PROCR-219Gly increases plasma levels of (activated) protein C through endothelial protein C receptor (EPCR) ectodomain shedding in endothelial cells, attenuating leukocyte-endothelial cell adhesion and vascular inflammation. We also associate PROCR-219Gly with an increased pro-thrombotic state via coagulation factor VII, a ligand of EPCR. Our study, which links PROCR-219Gly to CAD through anti-inflammatory mechanisms and to VTE through pro-thrombotic mechanisms, provides a framework to reveal the mechanisms underlying similar cross-phenotype associations.

Published
2022

31. Launchpad: A Programming Model for Distributed Machine Learning Research

Author

Yang, Fan, Barth-Maron, Gabriel, Stańczyk, Piotr, Hoffman, Matthew, Liu, Siqi, Kroiss, Manuel, Pope, Aedan, and Rrustemi, Alban

Subjects
Computer Science - Distributed, Parallel, and Cluster Computing, Computer Science - Artificial Intelligence, Computer Science - Machine Learning
Abstract

A major driver behind the success of modern machine learning algorithms has been their ability to process ever-larger amounts of data. As a result, the use of distributed systems in both research and production has become increasingly prevalent as a means to scale to this growing data. At the same time, however, distributing the learning process can drastically complicate the implementation of even simple algorithms. This is especially problematic as many machine learning practitioners are not well-versed in the design of distributed systems, let alone those that have complicated communication topologies. In this work we introduce Launchpad, a programming model that simplifies the process of defining and launching distributed systems that is specifically tailored towards a machine learning audience. We describe our framework, its design philosophy and implementation, and give a number of examples of common learning algorithms whose designs are greatly simplified by this approach.

Published
2021

32. Kidney length normative values - new percentiles by age and body surface area in Central European children and adolescents

Author

Obrycki, Lukasz, Sarnecki, Jedrzej, Lichosik, Marianna, Sopinska, Malgorzata, Placzynska, Malgorzata, Stanczyk, Malgorzata, and Mirecka, Julia

Subjects
Kidneys -- Measurement, Children -- Medical examination, Teenagers -- Medical examination, Youth -- Medical examination, Health
Abstract

Background Kidney size evaluation is an essential examination in pediatric nephrology. While body length/height is the best predictor of kidney length, age-based and body surface area (BSA)-based normative values may be useful in clinical practice or research. This study aimed to establish ultrasound-based kidney length lambda-mu-sigma (LMS) percentiles by age and BSA in healthy children. Methods In 1758 Polish and Lithuanian children (868 boys, 49%) aged 0-19 years, kidney length was measured using ultrasonography. In all participants, anthropometric measurements were taken and kidney function was evaluated based on serum creatinine concentration. Participants with chronic or kidney diseases, abnormal kidney function, or pathologies in sonographic examination were excluded from the analysis. Results Kidney length (median kidney length) increased progressively from infancy to the age of 18 years, from 60.1 to 114.2 mm in males, and from 57.3 to 105.2 mm in females. A gradual increase of kidney length (50.sup.th percentile) in relation to BSA (from 46.1 mm in infants with a BSA of 0-1.2 m.sup.2 to 118.3 mm in adolescents with a BSA of 2.6-2.8 m.sup.2) was also observed. LMS percentiles by age (stratified by sex) and BSA were determined and presented as graphs and tables of percentiles and LMS parameters by 1-year age intervals and 0.2 m.sup.2 of BSA, respectively. Conclusions We present the first age- and BSA-based kidney length LMS normative values based on the largest pediatric cohort to date, which can be used in both clinical practice and research studies. Graphical abstract A higher resolution version of the Graphical abstract is available as Supplementary information, Author(s): Lukasz Obrycki [sup.1] , Jedrzej Sarnecki [sup.2] , Marianna Lichosik [sup.1] , Malgorzata Sopinska [sup.3] , Malgorzata Placzynska [sup.3] , Malgorzata Stanczyk [sup.4] , Julia Mirecka [sup.4] , Agnieszka [...]

Published
2023
Full Text
View/download PDF

41. Attribute Relevance and Discretisation in Knowledge Discovery: A Study in Stylometric Domain

Author

Stańczyk, Urszula, Zielosko, Beata, Baron, Grzegorz, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Mikyška, Jiří, editor, de Mulatier, Clélia, editor, Paszynski, Maciej, editor, Krzhizhanovskaya, Valeria V., editor, Dongarra, Jack J., editor, and Sloot, Peter M.A., editor

Published
2023
Full Text
View/download PDF

42. Cognitive training incorporating temporal information processing improves linguistic and non-linguistic functions in people with aphasia

Author

Mateusz Choinski, Magdalena Stanczyk, and Aneta Szymaszek

Subjects
Medicine, Science
Abstract

Abstract People with aphasia (PWA) often present deficits in non-linguistic cognitive functions, such as executive functions, working memory, and temporal information processing (TIP), which intensify the associated speech difficulties and hinder the rehabilitation process. Therefore, training targeting non-linguistic cognitive function deficiencies may be useful in the treatment of aphasia. The present study compared the effects of the novel Dr. Neuronowski® training method (experimental training), which particularly emphasizes TIP, with the linguistic training commonly applied in clinical practice (control training). Thirty four PWA underwent linguistic and non-linguistic assessments before and after the training as well as a follow-up assessment. Patients were randomly assigned to either experimental (n = 18) or control groups (n = 16). The experimental training improved both non-linguistic functions (TIP and verbal short-term and working memory) and linguistic functions: phoneme discrimination, sentence comprehension, grammar comprehension, verbal fluency, and naming. In contrast, the control training improved only grammar comprehension and naming. The follow-up assessment confirmed the stability of the effects of both trainings over time. Thus, in PWA, Dr. Neuronowski® training appears to have broader benefits for linguistic and non-linguistic functions than does linguistic training. This provides evidence that Dr. Neuronowski® may be considered a novel tool with potential clinical applications.

Published
2023
Full Text
View/download PDF

44. Deep Graph Convolutional Networks for Wind Speed Prediction

Author

Stańczyk, Tomasz and Mehrkanoon, Siamak

Subjects
Computer Science - Machine Learning, I.2, I.5
Abstract

Wind speed prediction and forecasting is important for various business and management sectors. In this paper, we introduce new models for wind speed prediction based on graph convolutional networks (GCNs). Given hourly data of several weather variables acquired from multiple weather stations, wind speed values are predicted for multiple time steps ahead. In particular, the weather stations are treated as nodes of a graph whose associated adjacency matrix is learnable. In this way, the network learns the graph spatial structure and determines the strength of relations between the weather stations based on the historical weather data. We add a self-loop connection to the learnt adjacency matrix and normalize the adjacency matrix. We examine two scenarios with the self-loop connection setting (two separate models). In the first scenario, the self-loop connection is imposed as a constant additive. In the second scenario a learnable parameter is included to enable the network to decide about the self-loop connection strength. Furthermore, we incorporate data from multiple time steps with temporal convolution, which together with spatial graph convolution constitutes spatio-temporal graph convolution. We perform experiments on real datasets collected from weather stations located in cities in Denmark and the Netherlands. The numerical experiments show that our proposed models outperform previously developed baseline models on the referenced datasets. We provide additional insights by visualizing learnt adjacency matrices from each layer of our models., Comment: 10 pages, 8 figures

Published
2021

45. Progesterone from ovulatory menstrual cycles is an important cause of breast cancer

Author

Herjan J. T. Coelingh Bennink, Iman J. Schultz, Marcus Schmidt, V. Craig Jordan, Paula Briggs, Jan F. M. Egberts, Kristina Gemzell-Danielsson, Ludwig Kiesel, Kirsten Kluivers, Jan Krijgh, Tommaso Simoncini, Frank Z. Stanczyk, and Robert D. Langer

Subjects
Breast cancer, Menstrual cycles, Progesterone, Estrogens, Tumor doubling time, DNA replication, Neoplasms. Tumors. Oncology. Including cancer and carcinogens, RC254-282
Abstract

Abstract Many factors, including reproductive hormones, have been linked to a woman’s risk of developing breast cancer (BC). We reviewed the literature regarding the relationship between ovulatory menstrual cycles (MCs) and BC risk. Physiological variations in the frequency of MCs and interference with MCs through genetic variations, pathological conditions and or pharmaceutical interventions revealed a strong link between BC risk and the lifetime number of MCs. A substantial reduction in BC risk is observed in situations without MCs. In genetic or transgender situations with normal female breasts and estrogens, but no progesterone (P4), the incidence of BC is very low, suggesting an essential role of P4. During the MC, P4 has a strong proliferative effect on normal breast epithelium, whereas estradiol (E2) has only a minimal effect. The origin of BC has been strongly linked to proliferation associated DNA replication errors, and the repeated stimulation of the breast epithelium by P4 with each MC is likely to impact the epithelial mutational burden. Long-lived cells, such as stem cells, present in the breast epithelium, can carry mutations forward for an extended period of time, and studies show that breast tumors tend to take decades to develop before detection. We therefore postulate that P4 is an important factor in a woman’s lifetime risk of developing BC, and that breast tumors arising during hormonal contraception or after menopause, with or without menopausal hormone therapy, are the consequence of the outgrowth of pre-existing neoplastic lesions, eventually stimulated by estrogens and some progestins.

Published
2023
Full Text
View/download PDF

46. SmaAt-UNet: Precipitation Nowcasting using a Small Attention-UNet Architecture

Author

Trebing, Kevin, Stanczyk, Tomasz, and Mehrkanoon, Siamak

Subjects
Computer Science - Machine Learning, Electrical Engineering and Systems Science - Image and Video Processing, I.2, I.5
Abstract

Weather forecasting is dominated by numerical weather prediction that tries to model accurately the physical properties of the atmosphere. A downside of numerical weather prediction is that it is lacking the ability for short-term forecasts using the latest available information. By using a data-driven neural network approach we show that it is possible to produce an accurate precipitation nowcast. To this end, we propose SmaAt-UNet, an efficient convolutional neural networks-based on the well known UNet architecture equipped with attention modules and depthwise-separable convolutions. We evaluate our approaches on a real-life datasets using precipitation maps from the region of the Netherlands and binary images of cloud coverage of France. The experimental results show that in terms of prediction performance, the proposed model is comparable to other examined models while only using a quarter of the trainable parameters., Comment: 9 pages, 4 figures

Published
2020

47. What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study

Author

Andrychowicz, Marcin, Raichuk, Anton, Stańczyk, Piotr, Orsini, Manu, Girgin, Sertan, Marinier, Raphael, Hussenot, Léonard, Geist, Matthieu, Pietquin, Olivier, Michalski, Marcin, Gelly, Sylvain, and Bachem, Olivier

Subjects
Computer Science - Machine Learning, Statistics - Machine Learning
Abstract

In recent years, on-policy reinforcement learning (RL) has been successfully applied to many different continuous control tasks. While RL algorithms are often conceptually simple, their state-of-the-art implementations take numerous low- and high-level design decisions that strongly affect the performance of the resulting agents. Those choices are usually not extensively discussed in the literature, leading to discrepancy between published descriptions of algorithms and their implementations. This makes it hard to attribute progress in RL and slows down overall progress [Engstrom'20]. As a step towards filling that gap, we implement >50 such ``choices'' in a unified on-policy RL framework, allowing us to investigate their impact in a large-scale empirical study. We train over 250'000 agents in five continuous control environments of different complexity and provide insights and practical recommendations for on-policy training of RL agents.

Published
2020

48. Acme: A Research Framework for Distributed Reinforcement Learning

Author

Hoffman, Matthew W., Shahriari, Bobak, Aslanides, John, Barth-Maron, Gabriel, Momchev, Nikola, Sinopalnikov, Danila, Stańczyk, Piotr, Ramos, Sabela, Raichuk, Anton, Vincent, Damien, Hussenot, Léonard, Dadashi, Robert, Dulac-Arnold, Gabriel, Orsini, Manu, Jacq, Alexis, Ferret, Johan, Vieillard, Nino, Ghasemipour, Seyed Kamyar Seyed, Girgin, Sertan, Pietquin, Olivier, Behbahani, Feryal, Norman, Tamara, Abdolmaleki, Abbas, Cassirer, Albin, Yang, Fan, Baumli, Kate, Henderson, Sarah, Friesen, Abe, Haroun, Ruba, Novikov, Alex, Colmenarejo, Sergio Gómez, Cabi, Serkan, Gulcehre, Caglar, Paine, Tom Le, Srinivasan, Srivatsan, Cowie, Andrew, Wang, Ziyu, Piot, Bilal, and de Freitas, Nando

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence
Abstract

Deep reinforcement learning (RL) has led to many recent and groundbreaking advances. However, these advances have often come at the cost of both increased scale in the underlying architectures being trained as well as increased complexity of the RL algorithms used to train them. These increases have in turn made it more difficult for researchers to rapidly prototype new ideas or reproduce published RL algorithms. To address these concerns this work describes Acme, a framework for constructing novel RL algorithms that is specifically designed to enable agents that are built using simple, modular components that can be used at various scales of execution. While the primary goal of Acme is to provide a framework for algorithm development, a secondary goal is to provide simple reference implementations of important or state-of-the-art algorithms. These implementations serve both as a validation of our design decisions as well as an important contribution to reproducibility in RL research. In this work we describe the major design decisions made within Acme and give further details as to how its components can be used to implement various algorithms. Our experiments provide baselines for a number of common and state-of-the-art algorithms as well as showing how these algorithms can be scaled up for much larger and more complex environments. This highlights one of the primary advantages of Acme, namely that it can be used to implement large, distributed RL algorithms that can run at massive scales while still maintaining the inherent readability of that implementation. This work presents a second version of the paper which coincides with an increase in modularity, additional emphasis on offline, imitation and learning from demonstrations algorithms, as well as various new agents implemented as part of Acme., Comment: This work presents a second version of the paper which coincides with an increase in modularity, additional emphasis on offline, imitation and learning from demonstrations algorithms, as well as various new agents implemented as part of Acme

Published
2020

49. Longitudinal antimüllerian hormone and its correlation with pubertal milestones

Author

Smith, Meghan B, Ho, Jacqueline, Ma, Lihong, Lee, Miryoung, Czerwinski, Stefan A, Glenn, Tanya L, Cool, David R, Gagneux, Pascal, Stanczyk, Frank Z, McGinnis, Lynda K, and Lindheim, Steven R

Subjects
Paediatrics, Biomedical and Clinical Sciences, Contraception/Reproduction, Pediatric, Obesity, Clinical Research, Antimüllerian hormone, menarche, pubarche, puberty, thelarche
Abstract

ObjectiveTo examine the changes in AMH levels longitudinally over time and their relationship with both body composition, particularly abdominal adiposity, and milestones of pubertal development in female children.DesignSecondary analysis of a prospective, longitudinal study.SettingUniversity affiliated research center and laboratories.PatientsEighty-nine females were examined between 1990 and 2015 to study child growth and development.InterventionsDemographic, anthropometric, growth, and pubertal milestone data with serum samples stored and subsequently analyzed for AMH.Main outcome measuresLongitudinal change in AMH and predicted AMH levels based on body composition, age, and pubertal milestones including, pubarche, thelarche, and menarche.ResultsNatural log-transformed AMH (AMHlog) levels appeared to have a nonlinear relationship with age, decreasing between 10 and 14 years of age, increasing until 16 years. A mixed effect linear model demonstrated that increased abdominal adiposity (waist/height ratio, WHtR) was significantly associated with the predicted increased AMHlog levels (β=1.37). As females progressed through the Tanner stages, the model predicted decreasing AMHlog values when adjusting for age and WHtR.ConclusionsDeclining AMH levels during puberty may not be reflective of diminished ovarian reserve as observed in adults, but may suggest a permissive role of AMH in the activation of the hypothalamic-pituitary-ovarian axis.

Published
2021

50. SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference

Author

Espeholt, Lasse, Marinier, Raphaël, Stanczyk, Piotr, Wang, Ke, and Michalski, Marcin

Subjects
Computer Science - Machine Learning, Statistics - Machine Learning
Abstract

We present a modern scalable reinforcement learning agent called SEED (Scalable, Efficient Deep-RL). By effectively utilizing modern accelerators, we show that it is not only possible to train on millions of frames per second but also to lower the cost of experiments compared to current methods. We achieve this with a simple architecture that features centralized inference and an optimized communication layer. SEED adopts two state of the art distributed algorithms, IMPALA/V-trace (policy gradients) and R2D2 (Q-learning), and is evaluated on Atari-57, DeepMind Lab and Google Research Football. We improve the state of the art on Football and are able to reach state of the art on Atari-57 three times faster in wall-time. For the scenarios we consider, a 40% to 80% cost reduction for running experiments is achieved. The implementation along with experiments is open-sourced so results can be reproduced and novel ideas tried out., Comment: New version that includes changes made during the ICLR 2020 review process (https://openreview.net/forum?id=rkgvXlrKwH)

Published
2019

Catalog

Books, media, physical & digital resources
See catalog results