English
Related papers

Related papers: The Minimum Information Principle for Discriminati…

200 papers

Upper and lower bounds are obtained for the joint entropy of a collection of random variables in terms of an arbitrary collection of subset joint entropies. These inequalities generalize Shannon's chain rule for entropy as well as…

Information Theory · Computer Science 2024-05-07 Mokshay Madiman , Prasad Tetali

Meta-learning automatically infers an inductive bias by observing data from a number of related tasks. The inductive bias is encoded by hyperparameters that determine aspects of the model class or training algorithm, such as initialization…

Machine Learning · Computer Science 2020-11-10 Sharu Theresa Jose , Osvaldo Simeone , Giuseppe Durisi

The minimum information copula principle initially suggested in \cite{MeeBed97} is a maximum entropy-like approach for finding the least informative copula, if it exists, that satisfies a certain number of expectation constraints specified…

Probability · Mathematics 2026-05-04 Ivan Kojadinovic , Tommaso Martini

Social and real-world considerations such as robustness, fairness, social welfare and multi-agent tradeoffs have given rise to multi-distribution learning paradigms, such as collaborative learning, group distributionally robust…

Machine Learning · Computer Science 2024-04-04 Nika Haghtalab , Michael I. Jordan , Eric Zhao

We consider the estimation of a signal from the knowledge of its noisy linear random Gaussian projections. A few examples where this problem is relevant are compressed sensing, sparse superposition codes, and code division multiple access.…

Information Theory · Computer Science 2020-08-31 Jean Barbier , Nicolas Macris , Mohamad Dia , Florent Krzakala

Bayes estimators are well known to provide a means to incorporate prior knowledge that can be expressed in terms of a single prior distribution. However, when this knowledge is too vague to express with a single prior, an alternative…

Methodology · Statistics 2023-09-04 Hongxiang Qiu , Alex Luedtke

Bayesian hierarchical models are frequently used in practical data analysis contexts. One interpretation of these models is that they provide an indirect way of assigning a prior for unknown parameters, through the introduction of…

Machine Learning · Statistics 2026-05-01 Brendon J. Brewer

Estimating the entropy of a discrete random variable is a fundamental problem in information theory and related fields. This problem has many applications in various domains, including machine learning, statistics and data compression. Over…

Information Theory · Computer Science 2020-12-22 Yuval Shalev , Amichai Painsky , Irad Ben-Gal

We consider the estimation of a signal from the knowledge of its noisy linear random Gaussian projections, a problem relevant in compressed sensing, sparse superposition codes or code division multiple access just to cite few. There has…

Information Theory · Computer Science 2017-03-24 Jean Barbier , Mohamad Dia , Nicolas Macris , Florent Krzakala

We show state-of-the-art word representation learning methods maximize an objective function that is a lower bound on the mutual information between different parts of a word sequence (i.e., a sentence). Our formulation provides an…

Computation and Language · Computer Science 2019-11-27 Lingpeng Kong , Cyprien de Masson d'Autume , Wang Ling , Lei Yu , Zihang Dai , Dani Yogatama

This chapter provides a comprehensive and self-contained discussion of the most recent developments of information theory of networks. Maximum entropy models of networks are the least biased ensembles enforcing a set of constraints and are…

Disordered Systems and Neural Networks · Physics 2022-06-14 Ginestra Bianconi

Maximum entropy method is a constructive criterion for setting up a probability distribution maximally non-committal to missing information on the basis of partial knowledge, usually stated as constrains on expectation values of some…

Statistical Mechanics · Physics 2015-07-20 Jorge Fernandez-de-Cossio , Jorge Fernandez-de-Cossio Diaz

The ability of machine learning (ML) algorithms to generalize well to unseen data has been studied through the lens of information theory, by bounding the generalization error with the input-output mutual information (MI), i.e., the MI…

Machine Learning · Statistics 2024-06-07 Kimia Nadjahi , Kristjan Greenewald , Rickard Brüel Gabrielsson , Justin Solomon

The Maximum Mutual Information (MMI) criterion is different from the Least Error Rate (LER) criterion. It can reduce failing to report small probability events. This paper introduces the Channels Matching (CM) algorithm for the MMI…

Machine Learning · Computer Science 2019-01-30 Chenguang Lu

Estimating mutual information (MI) is a fundamental yet challenging task in data science and machine learning. This work proposes a new estimator for mutual information. Our main discovery is that a preliminary estimate of the data…

Machine Learning · Computer Science 2024-08-20 Yanzhi Chen , Zijing Ou , Adrian Weller , Yingzhen Li

The data processing inequality is an information-theoretic principle stating that the information content of a signal cannot be increased by processing the observations. In particular, it suggests that there is no benefit in enhancing the…

Machine Learning · Computer Science 2025-12-25 Roy Turgeman , Tom Tirer

In the analysis of any type of system, granting maximum information extraction from its data is non-trivial. Confidence in successful information extraction typically builds on prior knowledge of the studied system or on the user's…

Data Analysis, Statistics and Probability · Physics 2026-01-01 Matteo Becchi , Giovanni Maria Pavan

Unsupervised sentence embeddings learning has been recently dominated by contrastive learning methods (e.g., SimCSE), which keep positive pairs similar and push negative pairs apart. The contrast operation aims to keep as much information…

Computation and Language · Computer Science 2022-09-23 Shaobin Chen , Jie Zhou , Yuling Sun , Liang He

In most data-scientific approaches, the principle of Maximum Entropy (MaxEnt) is used to a posteriori justify some parametric model which has been already chosen based on experience, prior knowledge or computational simplicity. In a…

Methodology · Statistics 2022-06-29 Orestis Loukas , Ho Ryun Chung

The i.i.d. assumption is a useful idealization that underpins many successful approaches to supervised machine learning. However, its violation can lead to models that learn to exploit spurious correlations in the training data, rendering…

Machine Learning · Computer Science 2020-06-15 Daniel Pace , Alessandra Russo , Murray Shanahan