English
Related papers

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

200 papers

We provide a novel dimension-free uniform concentration bound for the empirical risk function of constrained logistic regression. Our bound yields a milder sufficient condition for a uniform law of large numbers than conditions derived by…

Statistics Theory · Mathematics 2024-10-15 Shogo Nakakita

An "entropy increasing to the maximum" result analogous to the entropic central limit theorem (Barron 1986; Artstein et al. 2004) is obtained in the discrete setting. This involves the thinning operation and a Poisson limit. Monotonic…

Information Theory · Computer Science 2009-11-18 Yaming Yu

Large transformer-based models are able to perform in-context few-shot learning, without being explicitly trained for it. This observation raises the question: what aspects of the training regime lead to this emergent behavior? Here, we…

The overarching goal of this paper is to derive excess risk bounds for learning from exp-concave loss functions in passive and sequential learning settings. Exp-concave loss functions encompass several fundamental problems in machine…

Machine Learning · Computer Science 2014-02-11 Mehrdad Mahdavi , Rong Jin

In the last three decades, several measures of complexity have been proposed. Up to this point, most of such measures have only been developed for finite spaces. In these scenarios the baseline distribution is uniform. This makes sense…

Information Theory · Computer Science 2021-11-15 Daniel Andrés Díaz-Pachón , Robert J. Marks

We examine a class of deep learning models with a tractable method to compute information-theoretic quantities. Our contributions are three-fold: (i) We show how entropies and mutual informations can be derived from heuristic statistical…

Machine Learning · Computer Science 2020-01-22 Marylou Gabrié , Andre Manoel , Clément Luneau , Jean Barbier , Nicolas Macris , Florent Krzakala , Lenka Zdeborová

Sampling from various kinds of distributions is an issue of paramount importance in statistics since it is often the key ingredient for constructing estimators, test procedures or confidence intervals. In many situations, the exact sampling…

Computation · Statistics 2016-12-06 Arnak S. Dalalyan

During the last two decades, concentration inequalities have been the subject of exciting developments in various areas, including convex geometry, functional analysis, statistical physics, high-dimensional statistics, pure and applied…

Information Theory · Computer Science 2015-02-26 Maxim Raginsky , Igal Sason

We present an algorithm for the statistical learning setting with a bounded exp-concave loss in $d$ dimensions that obtains excess risk $O(d \log(1/\delta)/n)$ with probability at least $1 - \delta$. The core technique is to boost the…

Machine Learning · Computer Science 2016-10-17 Nishant A. Mehta

In Statistics, log-concave density estimation is a central problem within the field of nonparametric inference under shape constraints. Despite great progress in recent years on the statistical theory of the canonical estimator, namely the…

Computation · Statistics 2023-03-01 Wenyu Chen , Rahul Mazumder , Richard J. Samworth

Stochastic interdependence of a probablility distribution on a product space is measured by its Kullback-Leibler distance from the exponential family of product distributions (called multi-information). Here we investigate low-dimensional…

Mathematical Physics · Physics 2016-01-08 Nihat Ay , Andreas Knauf

We study the query complexity of obtaining a relative Fisher information guarantee for sampling from a log-smooth non-log-concave distribution; this is a sampling analog of finding an approximate stationary point in optimization. Our…

Data Structures and Algorithms · Computer Science 2026-05-18 Sinho Chewi , Andre Wibisono

Though learning has become a core component of modern information processing, there is now ample evidence that it can lead to biased, unsafe, and prejudiced systems. The need to impose requirements on learning is therefore paramount,…

Machine Learning · Computer Science 2022-10-20 Luiz F. O. Chamon , Santiago Paternain , Miguel Calvo-Fullana , Alejandro Ribeiro

Classifier-guided diffusion models generate conditional samples by augmenting the reverse-time score with the gradient of the log-probability predicted by a probabilistic classifier. In practice, this classifier is usually obtained by…

Machine Learning · Statistics 2026-02-06 Sharan Sahu , Arisina Banerjee , Yuchen Wu

Information theory provides a mathematical foundation to measure uncertainty in belief. Belief is represented by a probability distribution that captures our understanding of an outcome's plausibility. Information measures based on…

Information Theory · Computer Science 2020-01-17 Jed A. Duersch , Thomas A. Catanach

We consider the problem of estimating the support size of a distribution $D$. Our investigations are pursued through the lens of distribution testing and seek to understand the power of conditional sampling (denoted as COND), wherein one is…

Data Structures and Algorithms · Computer Science 2022-11-23 Diptarka Chakraborty , Gunjan Kumar , Kuldeep S. Meel

We give a concentration inequality based on the premise that random variables take values within a particular region. The concentration inequality guarantees that, for any sequence of correlated random variables, the difference between the…

Probability · Mathematics 2020-02-21 Go Kato

We study the time evolution of the mutual information between the mass distributions in spatially separated but casually connected regions in an expanding universe. The evolution of the mutual information is primarily determined by the…

Cosmology and Nongalactic Astrophysics · Physics 2023-07-25 Biswajit Pandey

We review and formulate results concerning log-concavity and strong-log-concavity in both discrete and continuous settings. We show how preservation of log-concavity and strongly log-concavity on $\mathbb{R}$ under convolution follows from…

Statistics Theory · Mathematics 2014-04-24 Adrien Saumard , Jon A. Wellner

We prove an exponential decay concentration inequality to bound the tail probability of the difference between the log-likelihood of discrete random variables on a finite alphabet and the negative entropy. The concentration bound we derive…

Probability · Mathematics 2021-06-23 Yunpeng Zhao