English
Related papers

Related papers: Information Theoretic Bounds on Optimal Worst-case…

200 papers

We introduce a bottleneck method for learning data representations based on information deficiency, rather than the more traditional information sufficiency. A variational upper bound allows us to implement this method efficiently. The…

Information Theory · Computer Science 2020-11-05 Pradeep Kr. Banerjee , Guido Montúfar

The Chernoff bound is a well-known tool for obtaining a high probability bound on the expectation of a Bernoulli random variable in terms of its sample average. This bound is commonly used in statistical learning theory to upper bound the…

Machine Learning · Statistics 2022-05-18 Andrew Y. K. Foong , Wessel P. Bruinsma , David R. Burt

In label-noise learning, estimating the transition matrix has attracted more and more attention as the matrix plays an important role in building statistically consistent classifiers. However, it is very challenging to estimate the…

Machine Learning · Computer Science 2022-06-08 De Cheng , Tongliang Liu , Yixiong Ning , Nannan Wang , Bo Han , Gang Niu , Xinbo Gao , Masashi Sugiyama

The community detection problem involves making inferences about node labels in a graph, based on observing the graph edges. This paper studies the effect of additional, non-graphical side information on the phase transition of exact…

Information Theory · Computer Science 2019-01-30 Hussein Saad , Aria Nosratinia

We give tight statistical query (SQ) lower bounds for learnining halfspaces in the presence of Massart noise. In particular, suppose that all labels are corrupted with probability at most $\eta$. We show that for arbitrary $\eta \in…

Machine Learning · Computer Science 2022-01-25 Rajai Nasser , Stefan Tiegel

The noisy permutation channel is a useful abstraction introduced by Makur for point-to-point communication networks and biological storage. While the asymptotic capacity results exist for this model, the characterization of the second-order…

Information Theory · Computer Science 2024-06-24 Lugaoze Feng , Baoji Wang , Guocheng Lv , Xvnan Li , Luhua Wang , Ye jin

We provide matching upper and lower bounds of order $\sigma^2/\log(d/n)$ for the prediction error of the minimum $\ell_1$-norm interpolator, a.k.a. basis pursuit. Our result is tight up to negligible terms when $d \gg n$, and is the first…

Statistics Theory · Mathematics 2022-03-09 Guillaume Wang , Konstantin Donhauser , Fanny Yang

We explore the fundamental limits of heterogeneous distributed detection in an anonymous sensor network with n sensors and a single fusion center. The fusion center collects the single observation from each of the n sensors to detect a…

Information Theory · Computer Science 2018-07-31 Wei-Ning Chen , I-Hsiang Wang

In the community detection problem, one may have access to additional observations (side information) about the label of each node. This paper studies the effect of the quality and quantity of side information on the phase transition of…

Information Theory · Computer Science 2018-04-27 Hussein Saad , Ahmed Abotabl , Aria Nosratinia

We study error exponents for the problem of low-rate communication over a directed graph, where each edge in the graph represents a noisy communication channel, and there is a single source and destination. We derive maxflow-based…

Information Theory · Computer Science 2023-04-06 Yan Hao Ling , Jonathan Scarlett

Motivated by a greedy approach for generating {\it{information stable}} processes, we prove a universal maximum likelihood (ML) upper bound on the capacities of discrete information stable channels, including the binary erasure channel…

Information Theory · Computer Science 2018-05-21 Tongxin Li

The information bottleneck principle is an elegant and useful approach to representation learning. In this paper, we investigate the problem of representation learning in the context of reinforcement learning using the information…

Machine Learning · Computer Science 2019-11-14 Pei Yingjun , Hou Xinwen

In this work, we present a variety of novel information-theoretic generalization bounds for learning algorithms, from the supersample setting of Steinke & Zakynthinou (2020)-the setting of the "conditional mutual information" framework. Our…

Machine Learning · Statistics 2023-06-16 Ziqiao Wang , Yongyi Mao

The classical approach to system identification is based on stochastic assumptions about the measurement error, and provides estimates that have random nature. Worst-case identification, on the other hand, only assumes the knowledge of…

Systems and Control · Computer Science 2013-06-07 Fabrizio Dabbene , Mario Sznaier , Roberto Tempo

In the presence of noisy or incorrect labels, neural networks have the undesirable tendency to memorize information about the noise. Standard regularization techniques such as dropout, weight decay or data augmentation sometimes help, but…

Machine Learning · Computer Science 2020-11-23 Hrayr Harutyunyan , Kyle Reing , Greg Ver Steeg , Aram Galstyan

Deep Neural Nets (DNNs) learn latent representations induced by their downstream task, objective function, and other parameters. The quality of the learned representations impacts the DNN's generalization ability and the coherence of the…

Machine Learning · Computer Science 2024-02-13 Nir Weingarten , Zohar Yakhini , Moshe Butman , Ran Gilad-Bachrach

We consider the problem of identifying, from its first $m$ noisy moments, a probability distribution on $[0,1]$ of support $k<\infty$. This is equivalent to the problem of learning a distribution on $m$ observable binary random variables…

Machine Learning · Computer Science 2020-09-08 Spencer Gordon , Bijan Mazaheri , Leonard J. Schulman , Yuval Rabani

The group testing problem consists of determining a small set of defective items from a larger set of items based on a number of possibly-noisy tests, and is relevant in applications such as medical testing, communication protocols, pattern…

Information Theory · Computer Science 2023-09-19 Jonathan Scarlett , Oliver Johnson

We consider communication over binary-input memoryless output-symmetric channels using low-density parity-check codes and message-passing decoding. The asymptotic (in the length) performance of such a combination for a fixed number of…

Information Theory · Computer Science 2008-02-12 Satish Babu Korada , Ruediger Urbanke

Sample selection is a prevalent method in learning with noisy labels, where small-loss data are typically considered as correctly labeled data. However, this method may not effectively identify clean hard examples with large losses, which…

Machine Learning · Computer Science 2023-08-29 Suqin Yuan , Lei Feng , Tongliang Liu