English
Related papers

Related papers: Dimension-free Information Concentration via Exp-C…

200 papers

We present an information-theoretic framework for discrete diffusion models that yields principled estimators of log-likelihood using score-matching losses. Inspired by the I-MMSE identity for the Gaussian setup, we derive analogous results…

Machine Learning · Computer Science 2025-10-29 Moongyu Jeon , Sangwoo Shin , Dongjae Jeon , Albert No

Minimization of the (regularized) entropy of classification probabilities is a versatile class of discriminative clustering methods. The classification probabilities are usually defined through the use of some classical losses from…

Statistics Theory · Mathematics 2021-12-17 Edouard Genetay , Adrien Saumard , Rémi Coulaud

The overall predictive uncertainty of a trained predictor can be decomposed into separate contributions due to epistemic and aleatoric uncertainty. Under a Bayesian formulation, assuming a well-specified model, the two contributions can be…

Machine Learning · Computer Science 2021-10-22 Sharu Theresa Jose , Sangwoo Park , Osvaldo Simeone

Machine learning theory has mostly focused on generalization to samples from the same distribution as the training data. Whereas a better understanding of generalization beyond the training distribution where the observed distribution…

Machine Learning · Statistics 2019-05-29 Matias Vera , Pablo Piantanida , Leonardo Rey Vega

We study probability density functions that are log-concave. Despite the space of all such densities being infinite-dimensional, the maximum likelihood estimate is the exponential of a piecewise linear function determined by finitely many…

Bi-log-concavity of probability measures is a univariate extension of the notion of log-concavity that has been recently proposed in a statistical literature. Among other things, it has the nice property from a modelisation perspective to…

Probability · Mathematics 2019-03-20 Adrien Saumard

We extend the result of Ball and Nguyen on the jump of entropy under convolution for logconcave random vectors. We show that the result holds for any pair of vectors (not necessarily identically distributed) and that a similar inequality…

Functional Analysis · Mathematics 2021-11-08 Pierre Bizeul

We consider the problem of PAC-learning from distributed data and analyze fundamental communication complexity questions involved. We provide general upper and lower bounds on the amount of communication needed to learn well, showing that…

Machine Learning · Computer Science 2012-05-28 Maria-Florina Balcan , Avrim Blum , Shai Fine , Yishay Mansour

Concentration inequalities are indispensable tools for studying the generalization capacity of learning models. Hoeffding's and McDiarmid's inequalities are commonly used, giving bounds independent of the data distribution. Although this…

Machine Learning · Statistics 2017-02-21 Xinxing Wu , Junping Zhang

In recent years, self-supervised learning has played a pivotal role in advancing machine learning by allowing models to acquire meaningful representations from unlabeled data. An intriguing research avenue involves developing…

Machine Learning · Computer Science 2023-10-30 Denis Janiak , Jakub Binkowski , Piotr Bielak , Tomasz Kajdanowicz

This paper models information diffusion in a network of Large Language Models (LLMs) that is designed to answer queries from distributed datasets, where the LLMs can hallucinate the answer. We introduce a two-time-scale dynamical model for…

Social and Information Networks · Computer Science 2025-04-22 Adit Jain , Vikram Krishnamurthy , Yiming Zhang

We consider the problem of decision-making with side information and unbounded loss functions. Inspired by probably approximately correct learning model, we use a slightly different model that incorporates the notion of side information in…

Machine Learning · Computer Science 2007-07-13 Majid Fozunbal , Ton Kalker

We extend previously proposed measures of complexity, emergence, and self-organization to continuous distributions using differential entropy. This allows us to calculate the complexity of phenomena for which distributions are known. We…

Adaptation and Self-Organizing Systems · Physics 2016-04-01 Guillermo Santamaría-Bonfil , Nelson Fernández , Carlos Gershenson

Sufficient conditions are developed, under which the compound Poisson distribution has maximal entropy within a natural class of probability measures on the nonnegative integers. Recently, one of the authors [O. Johnson, {\em Stoch. Proc.…

Combinatorics · Mathematics 2013-03-20 Oliver Johnson , Ioannis Kontoyiannis , Mokshay Madiman

The Uniform Information Density (UID) hypothesis proposes that effective communication is achieved by maintaining a stable flow of information. In this work, we revisit this principle in the context of Large Language Model (LLM) reasoning,…

Artificial Intelligence · Computer Science 2026-04-20 Minju Gwak , Guijin Son , Jaehyung Kim

Entanglement growth and out-of-time-order correlators (OTOC) are used to assess the propagation of information in isolated quantum systems. In this work, using large scale exact time-evolution we show that for weakly disordered…

Disordered Systems and Neural Networks · Physics 2017-07-19 David J. Luitz , Yevgeny Bar Lev

We establish concentration inequalities in the class of ultra log-concave distributions. In particular, we show that ultra log-concave distributions satisfy Poisson concentration bounds. As an application, we derive concentration bounds for…

Probability · Mathematics 2021-10-04 Heshan Aravinda , Arnaud Marsiglietti , James Melbourne

A dispersive medium becomes entangled with zero-point fluctuations in the vacuum. We consider an arbitrary array of material bodies weakly interacting with a quantum field and compute the quantum mutual information between them. It is shown…

Quantum Physics · Physics 2015-06-08 Mohammad F. Maghrebi , Homer Reid

We establish the first tight lower bound of $\Omega(\log\log\kappa)$ on the query complexity of sampling from the class of strongly log-concave and log-smooth distributions with condition number $\kappa$ in one dimension. Whereas existing…

Statistics Theory · Mathematics 2021-06-11 Sinho Chewi , Patrik Gerber , Chen Lu , Thibaut Le Gouic , Philippe Rigollet

Information-theoretic Bayesian regret bounds of Russo and Van Roy capture the dependence of regret on prior uncertainty. However, this dependence is through entropy, which can become arbitrarily large as the number of actions increases. We…

Machine Learning · Statistics 2020-07-09 Shi Dong , Benjamin Van Roy
‹ Prev 1 3 4 5 6 7 10 Next ›