Search

Supplemental Material, sj-docx-2-tpx-10.1177_0192623321993425 for HistoNet: A Deep Learning-Based Model of Normal Histology by Holger Hoefling, Tobias Sing, Imtiaz Hossain, Julie Boisclair, Arno Doelemeyer, Thierry Flandre, Alessandro Piaia, Vincent Romanet, Gianluca Santarossa, Chandrassegar Saravanan, Esther Sutter, Oliver Turner, Kuno Wuersch and Pierre Moulin in Toxicologic Pathology

Supplemental Material, sj-docx-1-tpx-10.1177_0192623320987202 for Biomarker-Based Classification and Localization of Renal Lesions Using Learned Representations of Histology—A Machine Learning Approach to Histopathology by Christophe A. C. Freyre, Stephan Spiegel, Caroline Gubser Keller, Marc Vandemeulebroecke, Holger Hoefling, Valerie Dubost, Emre Cörek, Pierre Moulin and Imtiaz Hossain in Toxicologic Pathology

Supplemental Material, sj-docx-2-tpx-10.1177_0192623320987202 for Biomarker-Based Classification and Localization of Renal Lesions Using Learned Representations of Histology—A Machine Learning Approach to Histopathology by Christophe A. C. Freyre, Stephan Spiegel, Caroline Gubser Keller, Marc Vandemeulebroecke, Holger Hoefling, Valerie Dubost, Emre Cörek, Pierre Moulin and Imtiaz Hossain in Toxicologic Pathology

Supplemental Material, sj-docx-1-tpx-10.1177_0192623321993425 for HistoNet: A Deep Learning-Based Model of Normal Histology by Holger Hoefling, Tobias Sing, Imtiaz Hossain, Julie Boisclair, Arno Doelemeyer, Thierry Flandre, Alessandro Piaia, Vincent Romanet, Gianluca Santarossa, Chandrassegar Saravanan, Esther Sutter, Oliver Turner, Kuno Wuersch and Pierre Moulin in Toxicologic Pathology

Robust machine learning formulations have emerged to address the prevalent vulnerability of deep neural networks to adversarial examples. Our work draws the connection between optimal robust learning and the privacy-utility tradeoff problem, which is a generalization of the rate-distortion problem. The saddle point of the game between a robust classifier and an adversarial perturbation can be found via the solution of a maximum conditional entropy problem. This information-theoretic perspective sheds light on the fundamental tradeoff between robustness and clean data performance, which ultimately arises from the geometric structure of the underlying data distribution and perturbation constraints., Comment: 9 pages, 2 figures, accepted at 2021 IEEE International Symposium on Information Theory

Various adversarial audio attacks have recently been developed to fool automatic speech recognition (ASR) systems. We here propose a defense against such attacks based on the uncertainty introduced by dropout in neural networks. We show that our defense is able to detect attacks created through optimized perturbations and frequency masking on a state-of-the-art end-to-end ASR system. Furthermore, the defense can be made robust against attacks that are immune to noise reduction. We test our defense on Mozilla's CommonVoice dataset, the UrbanSound dataset, and an excerpt of the LibriSpeech dataset, showing that it achieves high detection accuracy in a wide range of scenarios., Comment: Accepted for publication at Interspeech 2020

The purpose of this manuscript is to derive new convergence results for several subgradient methods applied to minimizing nonsmooth convex functions with H��lderian growth. The growth condition is satisfied in many applications and includes functions with quadratic growth and weakly sharp minima as special cases. To this end there are three main contributions. First, for a constant and sufficiently small stepsize, we show that the subgradient method achieves linear convergence up to a certain region including the optimal set, with error of the order of the stepsize. Second, if appropriate problem parameters are known, we derive a decaying stepsize which obtains a much faster convergence rate than is suggested by the classical $O(1/\sqrt{k})$ result for the subgradient method. Thirdly we develop a novel "descending stairs" stepsize which obtains this faster convergence rate and also obtains linear convergence for the special case of weakly sharp functions. We also develop an adaptive variant of the "descending stairs" stepsize which achieves the same convergence rate without requiring an error bound constant which is difficult to estimate in practice., 50 pages. First revised version (under submission to Math Programming)

A problem of great interest in optimization is to minimize a sum of two closed, proper, and convex functions where one is smooth and the other has a computationally inexpensive proximal operator. In this paper we analyze a family of Inertial Forward-Backward Splitting (I-FBS) algorithms for solving this problem. We first apply a global Lyapunov analysis to I-FBS and prove weak convergence of the iterates to a minimizer in a real Hilbert space. We then show that the algorithms achieve local linear convergence for "sparse optimization", which is the important special case where the nonsmooth term is the $\ell_1$-norm. This result holds under either a restricted strong convexity or a strict complimentary condition and we do not require the objective to be strictly convex. For certain parameter choices we determine an upper bound on the number of iterations until the iterates are confined on a manifold containing the solution set and linear convergence holds. The local linear convergence result for sparse optimization holds for the Fast Iterative Shrinkage and Soft Thresholding Algorithm (FISTA) due to Beck and Teboulle which is a particular parameter choice for I-FBS. In spite of its optimal global objective function convergence rate, we show that FISTA is not optimal for sparse optimization with respect to the local convergence rate. We determine the locally optimal parameter choice for the I-FBS family. Finally we propose a method which inherits the excellent global rate of FISTA but also has excellent local rate., Comment: The proofs of Thms. 4.1, 5.1, 5.2, and 5.6 of this manuscript contain several errors. These errors have been fixed in a revised and rewritten manuscript entitled "Local and Global Convergence of a General Inertial Proximal Splitting Scheme" arxiv id. 1602.02726. We recommend reading this updated manuscript, available at arXiv:1602.02726

Solid pseudopapillary tumors (SPT) of the pancreas are rare neoplasms that occur mostly in young women. Despite of a low malignant potential, 10% to 15% of the cases have aggressive behavior with metastatic dissemination possibly leading to death. To date, no pathological factor can reliably predict the outcome of these tumours. Galectin-3, a major actor in the carcinogenesis of pancreatic ductal adenocarcinoma, has not been investigated in SPT. The presence of progesterone receptors is frequently reported in SPT, whereas that of estrogen receptor (ER) is unclear. We studied 5 cases of SPT consisting of 4 pancreatic tumors and 1 metastatic case. The morphological distinctive feature of metastatic nodules was the presence of polygonal or spindle cells with pleiomorphic nuclei and high mitotic count exhibiting a diffuse, infiltrative growth pattern. We found a strong expression of galectin-3 in all SPTs, whereas, interestingly, it was lower in metastatic nodules. Conversely, no galectin-3 expression was found in normal pancreatic endocrine cells or in neuroendocrine tumors. We suggest therefore that galectin-3 is a useful marker to distinguish SPT from neuroendocrine tumor, and also indicator of behavior because its low expression is associated with metastatic spreading. Moreover, the presence of galectin-3 in both SPT and pancreatic ducts rises the hypothesis of a posible ductal origin of these tumors. Specific antibodies for anti-ERalpha and anti-ERbeta demonstrated a strong expression of ERbeta whereas ERalpha was not detected. In conclusion, the present study brings the first evidence of the involvement of galectin-3 in SPT but also brought up clues which allowed to reconcile previously conflicting results on the presence of ER.

We derive the optimum second-order coding rates, known as second-order capacities, for erasure and list decoding. For erasure decoding for discrete memoryless channels, we show that second-order capacity is $\sqrt{V}\Phi^{-1}(\epsilon_t)$ where $V$ is the channel dispersion and $\epsilon_t$ is the total error probability, i.e., the sum of the erasure and undetected errors. We show numerically that the expected rate at finite blocklength for erasures decoding can exceed the finite blocklength channel coding rate. We also show that the analogous result also holds for lossless source coding with decoder side information, i.e., Slepian-Wolf coding. For list decoding, we consider list codes of deterministic size that scales as $\exp(\sqrt{n}l)$ and show that the second-order capacity is $l+\sqrt{V}\Phi^{-1}(\epsilon)$ where $\epsilon$ is the permissible error probability. We also consider lists of polynomial size $n^\alpha$ and derive bounds on the third-order coding rate in terms of the order of the polynomial $\alpha$. These bounds are tight for symmetric and singular channels. The direct parts of the coding theorems leverage on the simple threshold decoder and converses are proved using variants of the hypothesis testing converse., Comment: 18 pages, 1 figure; Submitted to IEEE Transactions on Information Theory; Shorter version to be presented at ISIT 2014

Collective intelligence, which aggregates the shared information from large crowds, is often negatively impacted by unreliable information sources with the low quality data. This becomes a barrier to the effective use of collective intelligence in a variety of applications. In order to address this issue, we propose a probabilistic model to jointly assess the reliability of sources and find the true data. We observe that different sources are often not independent of each other. Instead, sources are prone to be mutually influenced, which makes them dependent when sharing information with each other. High dependency between sources makes collective intelligence vulnerable to the overuse of redundant (and possibly incorrect) information from the dependent sources. Thus, we reveal the latent group structure among dependent sources, and aggregate the information at the group level rather than from individual sources directly. This can prevent the collective intelligence from being inappropriately dominated by dependent sources. We will also explicitly reveal the reliability of groups, and minimize the negative impacts of unreliable groups. Experimental results on real-world data sets show the effectiveness of the proposed approach with respect to existing algorithms.

Publication in the conference proceedings of EUSIPCO, Antalya, Turkey, 2005

Capacity formulas and random-coding exponents are derived for a generalized family of Gel'fand-Pinsker coding problems. These exponents yield asymptotic upper bounds on the achievable log probability of error. In our model, information is to be reliably transmitted through a noisy channel with finite input and output alphabets and random state sequence, and the channel is selected by a hypothetical adversary. Partial information about the state sequence is available to the encoder, adversary, and decoder. The design of the transmitter is subject to a cost constraint. Two families of channels are considered: 1) compound discrete memoryless channels (CDMC), and 2) channels with arbitrary memory, subject to an additive cost constraint, or more generally to a hard constraint on the conditional type of the channel output given the input. Both problems are closely connected. The random-coding exponent is achieved using a stacked binning scheme and a maximum penalized mutual information decoder, which may be thought of as an empirical generalized Maximum a Posteriori decoder. For channels with arbitrary memory, the random-coding exponents are larger than their CDMC counterparts. Applications of this study include watermarking, data hiding, communication in presence of partially known interferers, and problems such as broadcast channels, all of which involve the fundamental idea of binning., Comment: to appear in IEEE Transactions on Information Theory, without Appendices G and H