English
Related papers

Related papers: Robust Generalization via $\alpha$-Mutual Informat…

200 papers

Since the celebrated works of Russo and Zou (2016,2019) and Xu and Raginsky (2017), it has been well known that the generalization error of supervised learning algorithms can be bounded in terms of the mutual information between their input…

Machine Learning · Statistics 2022-07-20 Gábor Lugosi , Gergely Neu

We establish a connection between distributionally robust optimization (DRO) and classical robust statistics. We demonstrate that this connection arises naturally in the context of estimation under data corruption, where the goal is to…

Optimization and Control · Mathematics 2024-10-21 Gabriel Chan , Bart Van Parys , Amine Bennouna

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

Many evaluation measures are used to evaluate social biases in masked language models (MLMs). However, we find that these previously proposed evaluation measures are lacking robustness in scenarios with limited datasets. This is because…

Computation and Language · Computer Science 2024-01-23 Yang Liu

For generic systems exhibiting power law behaviors, and hence multiscale dependencies, we propose a new, and yet simple, tool to analyze multifractality and intermittency, after noticing that these concepts are directly related to the…

Statistical Mechanics · Physics 2018-01-24 Carlos Granero-Belinchon , Stephane G. Roux , Nicolas B. Garnier

In this paper, the worst-case probability measure over the data is introduced as a tool for characterizing the generalization capabilities of machine learning algorithms. More specifically, the worst-case probability measure is a Gibbs…

Machine Learning · Computer Science 2023-12-20 Xinying Zou , Samir M. Perlaza , Iñaki Esnaola , Eitan Altman

We consider the problem of parameter estimation in a Bayesian setting and propose a general lower-bound that includes part of the family of $f$-Divergences. The results are then applied to specific settings of interest and compared to other…

Information Theory · Computer Science 2022-05-19 Adrien Vandenbroucque , Amedeo Roberto Esposito , Michael Gastpar

Randomness in scientific estimation is generally assumed to arise from unmeasured or uncontrolled factors. However, when combining subjective probability estimates, heterogeneity stemming from people's cognitive or information diversity is…

Methodology · Statistics 2015-05-28 Ville Satopää , Robin Pemantle , Lyle Ungar

Generalization error bounds are critical to understanding the performance of machine learning models. In this work, building upon a new bound of the expected value of an arbitrary function of the population and empirical risk of a learning…

Information Theory · Computer Science 2021-05-07 Gholamali Aminian , Laura Toni , Miguel R. D. Rodrigues

Meta-learning, or "learning to learn", refers to techniques that infer an inductive bias from data corresponding to multiple related tasks with the goal of improving the sample efficiency for new, previously unobserved, tasks. A key…

Machine Learning · Computer Science 2021-02-24 Sharu Theresa Jose , Osvaldo Simeone

In this work, we connect the problem of bounding the expected generalisation error with transportation-cost inequalities. Exposing the underlying pattern behind both approaches we are able to generalise them and go beyond Kullback-Leibler…

Information Theory · Computer Science 2022-03-28 Amedeo Roberto Esposito , Michael Gastpar

Maximal $\alpha$-leakage is a tunable measure of information leakage based on the accuracy of guessing an arbitrary function of private data based on public data. The parameter $\alpha$ determines the loss function used to measure the…

Information Theory · Computer Science 2019-04-08 Jiachun Liao , Lalitha Sankar , Oliver Kosut , Flavio P. Calmon

We present a variational characterization for the R\'{e}nyi divergence of order infinity. Our characterization is related to guessing: the objective functional is a ratio of maximal expected values of a gain function applied to the…

Information Theory · Computer Science 2022-05-03 Gowtham R. Kurri , Oliver Kosut , Lalitha Sankar

We introduce an alternative closed form lower bound on the Gaussian process ($\mathcal{GP}$) likelihood based on the R\'enyi $\alpha$-divergence. This new lower bound can be viewed as a convex combination of the Nystr\"om approximation and…

Machine Learning · Statistics 2023-07-04 Xubo Yue , Raed Kontar

We consider the problem of estimating probability density functions based on sample data, using a finite mixture of densities from some component class. To this end, we introduce the $h$-lifted Kullback--Leibler (KL) divergence as a…

Machine Learning · Statistics 2024-12-24 Mark Chiu Chong , Hien Duy Nguyen , TrungTin Nguyen

We consider a natural measure of relevance: the reduction in optimal prediction risk in the presence of side information. For any given loss function, this relevance measure captures the benefit of side information for performing inference…

Information Theory · Computer Science 2015-12-23 Jiantao Jiao , Thomas Courtade , Kartik Venkat , Tsachy Weissman

Estimating the Shannon entropy of a discrete distribution from which we have only observed a small sample is challenging. Estimating other information-theoretic metrics, such as the Kullback-Leibler divergence between two sparsely sampled…

Data Analysis, Statistics and Probability · Physics 2023-02-24 Angelo Piga , Lluc Font-Pomarol , Marta Sales-Pardo , Roger Guimerà

Importance sampling approximates expectations with respect to a target measure by using samples from a proposal measure. The performance of the method over large classes of test functions depends heavily on the closeness between both…

Computation · Statistics 2016-09-01 Daniel Sanz-Alonso

Mutual information is one of the essential building blocks of information theory. Yet, it is only finitely defined for distributions with fast decaying tails on a countable joint alphabet of two random elements. The unboundedness of mutual…

Information Theory · Computer Science 2019-07-15 Zhiyi Zhang

Many practical studies rely on hypothesis testing procedures applied to data sets with missing information. An important part of the analysis is to determine the impact of the missing data on the performance of the test, and this can be…

Methodology · Statistics 2011-02-15 Dan L. Nicolae , Xiao-Li Meng , Augustine Kong
‹ Prev 1 4 5 6 7 8 10 Next ›