English
Related papers

Related papers: Rate-Distortion Bounds on Bayes Risk in Supervised…

200 papers

In statistical learning theory, determining the sample complexity of realizable binary classification for VC classes was a long-standing open problem. The results of Simon and Hanneke established sharp upper bounds in this setting. However,…

Machine Learning · Computer Science 2023-04-19 Ishaq Aden-Ali , Yeshwanth Cherapanamjeri , Abhishek Shetty , Nikita Zhivotovskiy

Recent work in unsupervised representation learning has focused on learning deep directed latent-variable models. Fitting these models by maximizing the marginal likelihood or evidence is typically intractable, thus a common approximation…

Machine Learning · Computer Science 2018-02-15 Alexander A. Alemi , Ben Poole , Ian Fischer , Joshua V. Dillon , Rif A. Saurous , Kevin Murphy

We consider lossy compression of a binary symmetric source by means of a low-density generator-matrix code. We derive two lower bounds on the rate distortion function which are valid for any low-density generator-matrix code with a given…

Information Theory · Computer Science 2008-04-11 Shrinivas Kudekar , Ruediger Urbanke

In this paper, we establish generalization bounds for transductive learning algorithms in the context of information theory and PAC-Bayes, covering both the random sampling and the random splitting setting. First, we show that the…

Machine Learning · Computer Science 2025-01-22 Huayi Tang , Yong Liu

Fundamental rate-distortion-perception (RDP) trade-offs arise in applications requiring maintained perceptual quality of reconstructed data, such as neural image compression. When compressed data is transmitted over public communication…

Information Theory · Computer Science 2026-04-23 Gustaf Åhlgren , Onur Günlü

We consider the problem of predicting as well as the best linear combination of d given functions in least squares regression under L^\infty constraints on the linear combination. When the input distribution is known, there already exists…

Statistics Theory · Mathematics 2011-09-14 Jean-Yves Audibert , Olivier Catoni

In this paper, we explore bounds on the expected risk when using deep neural networks for supervised classification from an information theoretic perspective. Firstly, we introduce model risk and fitting error, which are derived from…

Machine Learning · Computer Science 2024-10-08 Binchuan Qi

In this paper, we study the sample complexity lower bounds for the exact recovery of parameters and for a positive excess risk of a feed-forward, fully-connected neural network for binary classification, using information-theoretic tools.…

Machine Learning · Statistics 2020-10-30 Xiaochen Yang , Jean Honorio

The enormous size of modern deep neural networks makes it challenging to deploy those models in memory and communication limited scenarios. Thus, compressing a trained model without a significant loss in performance has become an…

Information Theory · Computer Science 2019-01-25 Weihao Gao , Yu-Han Liu , Chong Wang , Sewoong Oh

Recently, there has been a significant focus on exploring the theoretical aspects of deep learning, especially regarding its performance in classification tasks. Bayesian deep learning has emerged as a unified probabilistic framework,…

Statistics Theory · Mathematics 2025-01-24 The Tien Mai

Learning from Label Proportions (LLP) is a weakly supervised problem in which the training data comprise bags, that is, groups of instances, each annotated only with bag-level class label proportions, and the objective is to learn a…

Machine Learning · Computer Science 2026-03-24 Tianhao Ma , Ximing Li , Changchun Li , Renchu Guan

This paper deals with rate distortion or source coding with fidelity criterion, in measure spaces, for a class of source distributions. The class of source distributions is described by a relative entropy constraint set between the true and…

Information Theory · Computer Science 2013-05-07 Farzad Rezaei , Charalambos D. Charalambous , Photios A. Stavrou

Lossy data compression lies at the heart of modern communication and storage systems. Shannon's rate-distortion theory provides the fundamental limit on how much a source can be compressed at a given fidelity, but it assumes infinitely long…

Information Theory · Computer Science 2026-03-10 Bhaskar Krishnamachari

We study learning algorithms when there is a mismatch between the distributions of the training and test datasets of a learning algorithm. The effect of this mismatch on the generalization error and model misspecification are quantified.…

Information Theory · Computer Science 2022-08-11 Saeed Masiha , Amin Gohari , Mohammad Hossein Yassaee , Mohammad Reza Aref

In this paper, we study the rate distortion function of the i.i.d sequence of multiplications of a Bernoulli $p$ random variable and a gaussian random variable $\sim N(0,1)$. We use a new technique in the derivation of the lower bound in…

Information Theory · Computer Science 2016-11-15 Cheng Chang

We use the PAC-Bayesian theory for the setting of learning-to-optimize. To the best of our knowledge, we present the first framework to learn optimization algorithms with provable generalization guarantees (PAC-Bayesian bounds) and explicit…

Machine Learning · Computer Science 2025-02-26 Michael Sucker , Jalal Fadili , Peter Ochs

We propose a new construction for low-density source codes with multiple parameters that can be tuned to optimize the performance of the code. In addition, we introduce a set of analysis techniques for deriving upper bounds for the expected…

Information Theory · Computer Science 2007-07-13 Emin Martinian , Martin J. Wainwright

This article studies the achievable guarantees on the error rates of certain learning algorithms, with particular focus on refining logarithmic factors. Many of the results are based on a general technique for obtaining bounds on the error…

Machine Learning · Computer Science 2016-09-13 Steve Hanneke

Rate distortion theory is concerned with optimally encoding a given signal class $\mathcal{S}$ using a budget of $R$ bits, as $R\to\infty$. We say that $\mathcal{S}$ can be compressed at rate $s$ if we can achieve an error of…

Functional Analysis · Mathematics 2020-08-04 Philipp Grohs , Andreas Klotz , Felix Voigtlaender

A standard approach in pattern classification is to estimate the distributions of the label classes, and then to apply the Bayes classifier to the estimates of the distributions in order to classify unlabeled examples. As one might expect,…

Machine Learning · Computer Science 2007-05-23 Nick Palmer , Paul W. Goldberg