English
Related papers

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

200 papers

Can we learn more from data than existed in the generating process itself? Can new and useful information be constructed from merely applying deterministic transformations to existing data? Can the learnable content in data be evaluated…

Machine Learning · Computer Science 2026-03-17 Marc Finzi , Shikai Qiu , Yiding Jiang , Pavel Izmailov , J. Zico Kolter , Andrew Gordon Wilson

Since the emergence of research on improving the length extrapolation capabilities of large language models in 2021, some studies have made modifications to the scaling factor in the scaled dot-product attention mechanism as part of their…

Computation and Language · Computer Science 2025-01-28 Kewei Li , Yanwen Kong , Yiping Xu , Jianlin Su , Lan Huang , Ruochi Zhang , Fengfeng Zhou

Gibbs-ERM learning is a natural idealized model of learning with stochastic optimization algorithms (such as Stochastic Gradient Langevin Dynamics and ---to some extent--- Stochastic Gradient Descent), while it also arises in other…

Machine Learning · Computer Science 2019-02-06 Ilja Kuzborskij , Nicolò Cesa-Bianchi , Csaba Szepesvári

We seek an entropy estimator for discrete distributions with fully empirical accuracy bounds. As stated, this goal is infeasible without some prior assumptions on the distribution. We discover that a certain information moment assumption…

Information Theory · Computer Science 2022-12-27 Doron Cohen , Aryeh Kontorovich , Aaron Koolyk , Geoffrey Wolfer

Information theory provides tools to predict the performance of a learning algorithm on a given dataset. For instance, the accuracy of learning an unknown parameter can be upper bounded by reducing the learning task to hypothesis testing…

Quantum Physics · Physics 2026-04-21 Evan Peters

Threshold-type counts based on multivariate occupancy models with log concave marginals admit bounded size biased couplings under weak conditions, leading to new concentration of measure results for random graphs, germ-grain models in…

Probability · Mathematics 2017-05-25 Jay Bartroff , Larry Goldstein , Ümit Işlak

The estimation of a log-concave density on $\mathbb{R}$ is a canonical problem in the area of shape-constrained nonparametric inference. We present a Bayesian nonparametric approach to this problem based on an exponentiated Dirichlet…

Statistics Theory · Mathematics 2020-07-14 Ester Mariucci , Kolyan Ray , Botond Szabo

We consider the problem of stochastic convex optimization with exp-concave losses using Empirical Risk Minimization in a convex class. Answering a question raised in several prior works, we provide a $O( d / n + \log( 1 / \delta) / n )$…

Machine Learning · Computer Science 2023-07-06 Nikita Puchkin , Nikita Zhivotovskiy

We study a likelihood ratio test for the location of the mode of a log-concave density. Our test is based on comparison of the log-likelihoods corresponding to the unconstrained maximum likelihood estimator of a log-concave density and the…

Statistics Theory · Mathematics 2018-06-05 Charles R. Doss , Jon A. Wellner

The entropy of network ensembles characterizes the amount of information encoded in the network structure, and can be used to quantify network complexity, and the relevance of given structural properties observed in real network datasets…

Disordered Systems and Neural Networks · Physics 2014-06-18 Kartik Anand , Dimitri Krioukov , Ginestra Bianconi

We study the problem of estimating multivariate log-concave probability density functions. We prove the first sample complexity upper bound for learning log-concave densities on $\mathbb{R}^d$, for all $d \geq 1$. Prior to our work, no…

Machine Learning · Computer Science 2017-06-07 Ilias Diakonikolas , Daniel M. Kane , Alistair Stewart

We consider discrete stochastic processes, modeled by classical master equations, on networks. The temporal growth of the lack of information about the system is captured by its non-equilibrium entropy, defined via the transition…

Statistical Mechanics · Physics 2017-04-26 Oliver Muelken , Sarah Heinzelmann , Maxim Dolgushev

We present theoretical properties of the log-concave maximum likelihood estimator of a density based on an independent and identically distributed sample in $\mathbb{R}^d$. Our study covers both the case where the true underlying density is…

Statistics Theory · Mathematics 2009-09-01 Madeleine Cule , Richard Samworth

We propose a new discretization of the mirror-Langevin diffusion and give a crisp proof of its convergence. Our analysis uses relative convexity/smoothness and self-concordance, ideas which originated in convex optimization, together with a…

Statistics Theory · Mathematics 2021-10-26 Kwangjun Ahn , Sinho Chewi

Shape constraints yield flexible middle grounds between fully nonparametric and fully parametric approaches to modeling distributions of data. The specific assumption of log-concavity is motivated by applications across economics, survival…

Methodology · Statistics 2024-04-16 Robin Dunn , Aditya Gangrade , Larry Wasserman , Aaditya Ramdas

We present a new approach for inference about a log-concave distribution: Instead of using the method of maximum likelihood, we propose to incorporate the log-concavity constraint in an appropriate nonparametric confidence set for the cdf…

Statistics Theory · Mathematics 2022-05-10 Guenther Walther , Alnur Ali , Xinyue Shen , Stephen Boyd

We study the Shannon entropy of the cluster size distribution in classical as well as explosive percolation, in order to estimate the uncertainty in the sizes of randomly chosen clusters. At the critical point the cluster size distribution…

Disordered Systems and Neural Networks · Physics 2015-08-18 T. M. Vieira , G. M. Viswanathan , L. R. da Silva

The aim of this paper is to provide several novel upper bounds on the excess risk with a primal focus on classification problems. We suggest two approaches and the obtained bounds are represented via the distribution dependent local…

Statistics Theory · Mathematics 2018-03-13 Nikita Zhivotovskiy

We propose a method for estimating a log-concave density on $\mathbb R^d$ from samples, under the assumption that there exists an orthogonal transformation that makes the components of the random vector independent. While log-concave…

Statistics Theory · Mathematics 2024-12-20 Sharvaj Kubal , Christian Campbell , Elina Robeva

Understanding the dimension dependency of computational complexity in high-dimensional sampling problem is a fundamental problem, both from a practical and theoretical perspective. Compared with samplers with unbiased stationary…

Machine Learning · Computer Science 2024-03-12 Xunpeng Huang , Hanze Dong , Difan Zou , Tong Zhang