English
Related papers

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

200 papers

The information bottleneck (IB) approach is popular to improve the generalization, robustness and explainability of deep neural networks. Essentially, it aims to find a minimum sufficient representation $\mathbf{t}$ by striking a trade-off…

Machine Learning · Computer Science 2024-04-30 Shujian Yu , Xi Yu , Sigurd Løkse , Robert Jenssen , Jose C. Principe

Bayesian optimization based on the Gaussian process upper confidence bound (GP-UCB) offers a theoretical guarantee for optimizing black-box functions. In practice, however, black-box functions often involve input uncertainty. To handle such…

Machine Learning · Statistics 2025-07-24 Yu Inatsu

$f$-divergences are a general class of divergences between probability measures which include as special cases many commonly used divergences in probability, mathematical statistics and information theory such as Kullback-Leibler…

Statistics Theory · Mathematics 2013-10-16 Adityanand Guntuboyina , Sujayam Saha , Geoffrey Schiebinger

For a regression model, we consider the risk of the maximum likelihood estimator with respect to $\alpha$-divergence, which includes the special cases of Kullback-Leibler divergence, Hellinger distance and $\chi^2$ divergence. The…

Statistics Theory · Mathematics 2017-09-12 Yo Sheena

The paper concerns the rates of power-law growth of mutual information computed for a stationary measure or for a universal code. The rates are called Hilberg exponents and four such quantities are defined for each measure and each code:…

Information Theory · Computer Science 2020-03-11 Łukasz Dȩbowski

Mutual information is commonly used as a measure of similarity between competing labelings of a given set of objects, for example to quantify performance in classification and community detection tasks. As argued recently, however, the…

Social and Information Networks · Computer Science 2025-07-17 Maximilian Jerdee , Alec Kirkley , M. E. J. Newman

The Chernoff information between two probability measures is a statistical divergence measuring their deviation defined as their maximally skewed Bhattacharyya distance. Although the Chernoff information was originally introduced for…

Information Theory · Computer Science 2022-10-04 Frank Nielsen

We integrate information-theoretic concepts into the design and analysis of optimistic algorithms and Thompson sampling. By making a connection between information-theoretic quantities and confidence bounds, we obtain results that relate…

Machine Learning · Statistics 2019-11-25 Xiuyuan Lu , Benjamin Van Roy

We provide novel bounds on average treatment effects (on the treated) that are valid under an unconfoundedness assumption. Our bounds are designed to be robust in challenging situations, for example, when the conditioning variables take on…

Econometrics · Economics 2026-05-12 Sokbae Lee , Martin Weidner

We study the problem of estimating a distribution over a finite alphabet from an i.i.d. sample, with accuracy measured in relative entropy (Kullback-Leibler divergence). While optimal bounds on the expected risk are known, high-probability…

Statistics Theory · Mathematics 2026-02-27 Jaouad Mourtada

In this paper we shall consider one parametric generalization of some non-symmetric divergence measures. The \textit{non-symmetric divergence measures} are such as: Kullback-Leibler \textit{relative information}, $\chi…

Statistics Theory · Mathematics 2007-06-13 Pranesh Kumar , Inder Jeet Taneja

The distributionally robust Markov Decision Process (MDP) approach asks for a distributionally robust policy that achieves the maximal expected total reward under the most adversarial distribution of uncertain parameters. In this paper, we…

Systems and Control · Computer Science 2018-10-10 Zhi Chen , Pengqian Yu , William B. Haskell

We studied the mutual information between a stimulus and a large system consisting of stochastic, statistically independent elements that respond to a stimulus. The Mutual Information (MI) of the system saturates exponentially with system…

Statistical Mechanics · Physics 2009-11-07 Kukjin Kang , Haim Sompolinsky

This paper is devoted to the mathematical study of some divergences based on the mutual information well-suited to categorical random vectors. These divergences are generalizations of the "entropy distance" and "information distance". Their…

Statistics Theory · Mathematics 2016-08-16 Jean-François Coeurjolly , Rémy Drouilhet , Jean-François Robineau

The problem of robust binary hypothesis testing is studied. Under both hypotheses, the data-generating distributions are assumed to belong to uncertainty sets constructed through moments; in particular, the sets contain distributions whose…

Statistics Theory · Mathematics 2024-01-09 Akshayaa Magesh , Zhongchang Sun , Venugopal V. Veeravalli , Shaofeng Zou

Robust statistics traditionally focuses on outliers, or perturbations in total variation distance. However, a dataset could be corrupted in many other ways, such as systematic measurement errors and missing covariates. We generalize the…

Statistics Theory · Mathematics 2020-12-15 Banghua Zhu , Jiantao Jiao , Jacob Steinhardt

In this paper, we propose a novel robust stochastic optimization approach with a distinctive consideration for rare events, in which divergence measures are used to bound the event-wise ambiguity sets. This is done by using the Poisson…

Optimization and Control · Mathematics 2021-09-14 Aakil M. Caunhye , Douglas Alem

The traditional notion of generalization---i.e., learning a hypothesis whose empirical error is close to its true error---is surprisingly brittle. As has recently been noted in [DFH+15b], even if several algorithms have this guarantee in…

Data Structures and Algorithms · Computer Science 2016-06-03 Rachel Cummings , Katrina Ligett , Kobbi Nissim , Aaron Roth , Zhiwei Steven Wu

The information-theoretic framework of Russo and J. Zou (2016) and Xu and Raginsky (2017) provides bounds on the generalization error of a learning algorithm in terms of the mutual information between the algorithm's output and the training…

Machine Learning · Statistics 2020-10-26 Mahdi Haghifam , Jeffrey Negrea , Ashish Khisti , Daniel M. Roy , Gintare Karolina Dziugaite

The semiparametric estimation approach, which includes inverse-probability-weighted and doubly robust estimation using propensity scores, is a standard tool in causal inference, and it is rapidly being extended in various directions. On the…

Methodology · Statistics 2022-12-29 Takamichi Baba , Yoshiyuki Ninomiya