English
Related papers

Related papers: Generalized Mixability via Entropic Duality

200 papers

One fundamental goal in any learning algorithm is to mitigate its risk for overfitting. Mathematically, this requires that the learning algorithm enjoys a small generalization risk, which is defined either in expectation or in probability.…

Machine Learning · Computer Science 2016-10-04 Ibrahim Alabdulmohsin

Domain generalization (DG) aims to learn a generalizable model from multiple training domains such that it can perform well on unseen target domains. A popular strategy is to augment training data to benefit generalization through methods…

Computer Vision and Pattern Recognition · Computer Science 2023-11-29 Wang Lu , Jindong Wang , Han Yu , Lei Huang , Xiang Zhang , Yiqiang Chen , Xing Xie

In its continuous version, the entropy functional measuring the information content of a given probability density may be plagued by a "measure" problem that results from improper weighting of phase space. This issue is addressed…

Statistical Mechanics · Physics 2011-06-08 P. Maynar , E. Trizac

Although neural networks can solve very complex machine-learning problems, the theoretical reason for their generalizability is still not fully understood. Here we use Wang-Landau Mote Carlo algorithm to calculate the entropy (logarithm of…

Statistical Mechanics · Physics 2022-07-06 Ge Zhang

Compact data representations are one approach for improving generalization of learned functions. We explicitly illustrate the relationship between entropy and cardinality, both measures of compactness, including how gradient descent on the…

Machine Learning · Computer Science 2021-12-07 Xu Ji , Lena Nehale-Ezzine , Maksym Korablyov

It has been widely recognized that adversarial examples can be easily crafted to fool deep networks, which mainly root from the locally non-linear behavior nearby input examples. Applying mixup in training provides an effective mechanism to…

Machine Learning · Computer Science 2020-02-21 Tianyu Pang , Kun Xu , Jun Zhu

We consider a problem of guessing, wherein an adversary is interested in knowing the value of the realization of a discrete random variable $X$ on observing another correlated random variable $Y$. The adversary can make multiple (say, $k$)…

Information Theory · Computer Science 2021-08-20 Gowtham R. Kurri , Oliver Kosut , Lalitha Sankar

Over the past decades, numerous loss functions have been been proposed for a variety of supervised learning tasks, including regression, classification, ranking, and more generally structured prediction. Understanding the core principles…

Machine Learning · Statistics 2020-03-03 Mathieu Blondel , André F. T. Martins , Vlad Niculae

Pseudoentropy characterizations provide a quantitatively precise demonstration of the close relationship between computational hardness and computational randomness. We prove a unified pseudoentropy characterization that generalizes and…

Computational Complexity · Computer Science 2025-09-05 Lunjia Hu , Salil Vadhan

Finite mixture models have long been used across a variety of fields in engineering and sciences. Recently there has been a great deal of interest in quantifying the convergence behavior of the \emph{mixing measure}, a fundamental object…

Statistics Theory · Mathematics 2025-09-05 Yun Wei , Sayan Mukherjee , XuanLong Nguyen

We study the continuity property of the generalized entropy as a function of the underlying probability distribution, defined with an action space and a loss function, and use this property to answer the basic questions in statistical…

Machine Learning · Computer Science 2022-01-04 Aolin Xu

Regularized empirical risk minimization with constrained labels (in contrast to fixed labels) is a remarkably general abstraction of learning. For common loss and regularization functions, this optimization problem assumes the form of a…

Machine Learning · Computer Science 2016-02-23 Iaroslav Shcherbatyi , Bjoern Andres

We give some results relating asymptotic characterisations of maximum entropy probability measures to characterisations of Bayes optimal classifiers. Our main theorems show that maximum entropy is a universally Bayes optimal decision rule…

Statistics Theory · Mathematics 2025-07-08 Dalton A R Sakthivadivel

Let $X$ be a discrete random variable with support $S$ and $f : S \to S^\prime$ be a bijection. Then it is well-known that the entropy of $X$ is the same as the entropy of $f(X)$. This entropy preservation property has been well-utilized to…

Information Theory · Computer Science 2007-07-13 Chandra Nair , Balaji Prabhakar , Devavrat Shah

The entropy change that occurs upon mixing two fluids has remained an intriguing topic since the dawn of statistical mechanics. In this work, we generalize the grand-isobaric ensemble to mixtures, and develop a Monte Carlo algorithm for the…

Statistical Mechanics · Physics 2023-02-02 Caroline Desgranges , Jerome Delhommelle

A generalization of a distribution increases the flexibility particularly in studying of a phenomenon and its properties. Many generalizations of continuous univariate distributions are available in literature. In this study, an…

Applications · Statistics 2024-08-30 Brijesh P. Singh , Sandeep Singh , Utpal Dhar Das

We study the parameter estimation problem in mixture models with observational nonidentifiability: the full model (also containing hidden variables) is identifiable, but the marginal (observed) model is not. Hence global maxima of the…

Machine Learning · Statistics 2020-02-20 A. E. Allahverdyan

Deep neural classifiers have recently found tremendous success in data-driven control systems. However, existing models suffer from a trade-off between accuracy and adversarial robustness. This limitation must be overcome in the control of…

Machine Learning · Computer Science 2024-06-05 Yatong Bai , Brendon G. Anderson , Somayeh Sojoudi

Some properties of generalized convexity for sets and for functions are identified in case of the reliability polynomials of two dual minimal networks. A method of approximating the reliability polynomials of two dual minimal network is…

Discrete Mathematics · Computer Science 2021-12-14 Gabriela Cristescu , Vlad-Florin Dragoi , Sorin-Horatiu Hoara

We describe and develop a close relationship between two problems that have customarily been regarded as distinct: that of maximizing entropy, and that of minimizing worst-case expected loss. Using a formulation grounded in the equilibrium…

Statistics Theory · Mathematics 2007-06-13 Peter D. Grunwald , A. Philip Dawid