Search

Your search keyword '"Cesa-Bianchi, Nicolò"' showing total 438 results
Start Over Author "Cesa-Bianchi, Nicolò"
438 results on '"Cesa-Bianchi, Nicolò"'

101. Minimizing Regret with Label Efficient Prediction

Author

Cesa-Bianchi, Nicolò, Lugosi, Gábor, Stoltz, Gilles, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Carbonell, Jaime G., editor, Siekmann, Jörg, editor, Shawe-Taylor, John, editor, and Singer, Yoram, editor

Published
2004
Full Text
View/download PDF

103. A Second-Order Perceptron Algorithm

Author

Cesa-Bianchi, Nicolò, Conconi, Alex, Gentile, Claudio, Goos, G., editor, Hartmanis, J., editor, van Leeuwen, J., editor, Carbonell, Jaime G., editor, Siekmann, Jörg, editor, Kivinen, Jyrki, editor, and Sloan, Robert H., editor

Published
2002
Full Text
View/download PDF

112. A New Theoretical Framework for Fast and Accurate Online Decision-Making

Author

Cesa-Bianchi, Nicolò, Cesari, Tommaso, Mansour, Yishay, Perchet, Vianney, Università degli Studi di Milano [Milano] (UNIMI), Toulouse School of Economics (TSE), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-École des hautes études en sciences sociales (EHESS)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), Artificial and Natural Intelligence Toulouse Institute (ANITI), Tel Aviv University [Tel Aviv], Google Research, Centre de Recherche en Économie et STatistique (CREST), École Nationale de la Statistique et de l'Administration Économique (ENSAE Paris), Criteo AI Lab, Criteo [Paris], and ANR-19-P3IA-0004,ANITI,Artificial and Natural Intelligence Toulouse Institute(2019)

Subjects
[STAT.ML]Statistics [stat]/Machine Learning [stat.ML]
Abstract

We introduce a novel theoretical framework for Return On Investment (ROI) maximization in repeated decision-making. Our setting is motivated by the use case of companies that regularly receive proposals for technological innovations and want to quickly decide whether they are worth implementing. We design an algorithm for learning ROI-maximizing decision-making policies over a sequence of innovation proposals. Our algorithm provably converges to an optimal policy in class $\Pi$ at a rate of order $\min\big\{1/(N\Delta^2), N^{-1/3}\}$, where $N$ is the number of innovations and $\Delta$ is the suboptimality gap in $\Pi$. A significant hurdle of our formulation, which sets it aside from other online learning problems such as bandits, is that running a policy does not provide an unbiased estimate of its performance.

Published
2021

115. Fast and Accurate Repeated Decision Making

Author

Cesa-Bianchi, Nicolò, Cesari, Tommaso, Mansour, Yishay, Perchet, Vanney, Università degli studi di Milano [Milano], Toulouse School of Economics (TSE), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-École des hautes études en sciences sociales (EHESS)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), Google Research, Criteo AI Lab, Criteo [Paris], ANR-19-P3IA-0004,ANITI,Artificial and Natural Intelligence Toulouse Institute(2019), Université Toulouse 1 Capitole (UT1)-École des hautes études en sciences sociales (EHESS)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), Tel Aviv University [Tel Aviv], Centre de Recherche en Économie et STatistique (CREST), Ecole Nationale de la Statistique et de l'Analyse Economique (ENSAE), and Ecole Nationale de la Statistique et de l'Analyse Economique

Subjects
[STAT.ML]Statistics [stat]/Machine Learning [stat.ML]
Abstract

We study a setting in which a learner faces a sequence of decision tasks and is required to make good decisions as quickly as possible. Each task n is associated with a pair (Xn, µn), where Xn is a random variable and µn is its (unknown and potentially negative) expectation. The learner can draw arbitrarily many i.i.d. samples of Xn but its expectation µn is never revealed. After some sampling is done, the learner can decide to stop and either accept the task, gaining µn as a reward, or reject it, getting zero reward instead. A distinguishing feature of our model is that the learner's performance is measured as the expected cumulative reward divided by the expected cumulative number of drawn samples. The learner's goal is to converge to the per-sample reward of the optimal policy within a fixed class. We design an online algorithm with data-dependent theoretical guarantees for finite sets of policies, and analyze its extension to infinite classes of policies. A key technical aspect of this setting, which sets it aside from stochastic bandits, is the impossibility of obtaining unbiased estimates of the policy's performance objective.

Published
2021

127. The Game-Theoretic Approach to Machine Learning and Adaptation

Author

Cesa-Bianchi, Nicolò, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Nierstrasz, Oscar, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Sudan, Madhu, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Vardi, Moshe Y., Series editor, Weikum, Gerhard, Series editor, Goebel, Randy, editor, Siekmann, Jörg, editor, Wahlster, Wolfgang, editor, and Bouchachia, Abdelhamid, editor

Published
2011
Full Text
View/download PDF

137. Nonstochastic Bandits with Composite Anonymous Feedback.

Author

Cesa-Bianchi, Nicolò, Cesari, Tommaso, Colomboni, Roberto, Gentile, Claudio, and Mansour, Yishay

Subjects
*ROBBERS, *TIME perspective, *REGRET
Abstract

We investigate a nonstochastic bandit setting in which the loss of an action is not immediately charged to the player, but rather spread over the subsequent rounds in an adversarial way. The instantaneous loss observed by the player at the end of each round is then a sum of many loss components of previously played actions. This setting encompasses as a special case the easier task of bandits with delayed feedback, a well-studied framework where the player observes the delayed losses individually. Our first contribution is a general reduction transforming a standard bandit algorithm into one that can operate in the harder setting: We bound the regret of the transformed algorithm in terms of the stability and regret of the original algorithm. Then, we show that the transformation of a suitably tuned FTRL with Tsallis entropy has a regret of order (d+1)KT---------√, where d is the maximum delay, K is the number of arms, and T is the time horizon. Finally, we show that our results cannot be improved in general by exhibiting a matching (up to a log factor) lower bound on the regret of any algorithm operating in this setting. [ABSTRACT FROM AUTHOR]

Published
2022

143. Learning Task Specifications from Demonstrations.

Author

Vazquez-Chanlatte, Marcell, Bengio, Samy1, Wallach, Hanna M, Larochelle, Hugo, Grauman, Kristen, Cesa-Bianchi, Nicolò, Garnett, Roman, Vazquez-Chanlatte, Marcell, Jha, Susmit, Tiwari, Ashish, Ho, Mark K, Seshia, Sanjit A, Vazquez-Chanlatte, Marcell, Bengio, Samy1, Wallach, Hanna M, Larochelle, Hugo, Grauman, Kristen, Cesa-Bianchi, Nicolò, Garnett, Roman, Vazquez-Chanlatte, Marcell, Jha, Susmit, Tiwari, Ashish, Ho, Mark K, and Seshia, Sanjit A

Published
2018

145. On the Troll-Trust Model for Edge Sign Prediction in Social Networks

Author

Le Falher, Géraud, Cesa-Bianchi, Nicolò, Gentile, Claudio, Vitale, Fabio, Machine Learning in Information Networks (MAGNET), Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (CRIStAL), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS), Dipartimento di Scienze dell'Informazione [Milano], Università degli Studi di Milano [Milano] (UNIMI), Universitá degli Studi dell’Insubria, Aalto University School of Science and Technology [Aalto, Finland], INRIA Lille, Università degli Studi di Milano = University of Milan (UNIMI), Universitá degli Studi dell’Insubria = University of Insubria [Varese] (Uninsubria), Department of Informatics and System Sciences (Sapienza University of Rome), Università degli Studi di Roma 'La Sapienza' = Sapienza University [Rome] (UNIROMA), Università degli Studi di Roma 'La Sapienza' = Sapienza University [Rome], University of Lille, University of Milan, University of Insubria, Department of Computer Science, Aalto-yliopisto, and Aalto University

Subjects
Social and Information Networks (cs.SI), FOS: Computer and information sciences, Computer Science - Learning, Computer Science - Social and Information Networks, Machine Learning (cs.LG), [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract

In the problem of edge sign prediction, we are given a directed graph (representing a social network), and our task is to predict the binary labels of the edges (i.e., the positive or negative nature of the social relationships). Many successful heuristics for this problem are based on the troll-trust features, estimating at each node the fraction of outgoing and incoming positive/negative edges. We show that these heuristics can be understood, and rigorously analyzed, as approximators to the Bayes optimal classifier for a simple probabilistic model of the edge labels. We then show that the maximum likelihood estimator for this model approximately corresponds to the predictions of a Label Propagation algorithm run on a transformed version of the original social graph. Extensive experiments on a number of real-world datasets show that this algorithm is competitive against state-of-the-art classifiers in terms of both accuracy and scalability. Finally, we show that troll-trust features can also be used to derive online learning algorithms which have theoretical guarantees even when edges are adversarially labeled., Comment: v5: accepted to AISTATS 2017

Published
2016

147. Efficient Link Classification in Social Networks

Author

Cesa-Bianchi, Nicolò, Gentile, Claudio, Vitale, Fabio, Zappella, Giovanni, Dipartimento di Scienze dell'Informazione [Milano], Università degli Studi di Milano = University of Milan (UNIMI), Universitá degli Studi dell’Insubria = University of Insubria [Varese] (Uninsubria), Machine Learning in Information Networks (MAGNET), Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (CRIStAL), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS), Amazon Development Center Germany GmbH [Berlin], Amazon, Università degli Studi di Milano [Milano] (UNIMI), and Universitá degli Studi dell’Insubria

Subjects
[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [INFO]Computer Science [cs], ComputingMilieux_MISCELLANEOUS, [INFO.INFO-SI]Computer Science [cs]/Social and Information Networks [cs.SI], [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract

International audience

Published
2015

149. Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems

Author

Bubeck, Sébastien, Cesa-Bianchi, Nicolò, Bubeck, Sébastien, and Cesa-Bianchi, Nicolò

Subjects
Sequential analysis, Resource allocation--Mathematical models, Mathematical optimization
Abstract

Multi-armed bandit problems are the most basic examples of sequential decision problems with an exploration-exploitation trade-off. This is the balance between staying with the option that gave highest payoffs in the past and exploring new options that might give higher payoffs in the future. In this monograph, the focus is on two extreme cases in which the analysis of regret is particularly simple and elegant: independent and identically distributed payoffs and adversarial payoffs. Besides the basic setting of finitely many actions, it also analyzes some of the most important variants and extensions, such as the contextual bandit model.

Published
2012

150. Delay and Cooperation in Nonstochastic Bandits.

Author

Cesa-Bianchi, Nicolò, Gentile, Claudio, and Mansour, Yishay

Subjects
*MACHINE learning, *PROBABILITY theory, *SET theory, *GRAPH theory, *SPARSE approximations, *PARAMETER estimation
Abstract

We study networks of communicating learning agents that cooperate to solve a common nonstochastic bandit problem. Agents use an underlying communication network to get messages about actions selected by other agents, and drop messages that took more than d hops to arrive, where d is a delay parameter. We introduce Exp3-Coop, a cooperative version of the Exp3 algorithm and prove that with K actions and N agents the average per-agent regret after T rounds is at most of order √ (d + 1 + K/N α≤ (T lnK), where α≤d is the independence number of the d-th power of the communication graph G. We then show that for any connected graph, for d = √ K the regret bound is K1=4 √ T, strictly better than the minimax regret √ KT for noncooperating agents. More informed choices of d lead to bounds which are arbitrarily close to the full information minimax regret √T lnK when G is dense. When G has sparse components, we show that a variant of Exp3-Coop, allowing agents to choose their parameters according to their centrality in G, strictly improves the regret. Finally, as a by-product of our analysis, we provide the first characterization of the minimax regret for bandit learning with delay. [ABSTRACT FROM AUTHOR]

Published
2019

Catalog

Books, media, physical & digital resources
See catalog results