paper-with-me

Papers

Empirical Bernstein Inequalities for U-Statistics

2010-12-01 · NeurIPS 2010 12 · Thomas Peel, Sandrine Anthoine, Liva Ralaivola

We present original empirical Bernstein inequalities for U-statistics with bounded symmetric kernels q. They are expressed with respect to empirical estimates of either the variance of q or the conditional variance that appears in the Bernstein-type inequality for U-statistics derived by Arcones [2]. Our result subsumes other existing empirical Bernstein inequalities, as it reduces to them when U-statistics of order 1 are considered. In addition, it is based on a rather direct argument using two applications of the same (non-empirical) Bernstein inequality for U-statistics. We discuss potential applications of our new inequalities, especially in the realm of learning ranking/scoring functions. In the process, we exhibit an efficient procedure to compute the variance estimates for the special case of bipartite ranking that rests on a sorting argument. We also argue that our results may provide test set bounds and particularly interesting empirical racing algorithms for the problem of online learning of scoring functions.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Sharp Matrix Empirical Bernstein Inequalities

2024-11-14 · Hongjian Wang, Aaditya Ramdas

We present two sharp, closed-form empirical Bernstein inequalities for symmetric random matrices with bounded eigenvalues. By sharp, we mean that both inequalities adapt to the unknown variance in a tight manner: the dev…

Split-kl and PAC-Bayes-split-kl Inequalities for Ternary Random Variables

2022-06-01 · Yi-Shan Wu, Yevgeny Seldin

We present a new concentration of measure inequality for sums of independent bounded random variables, which we name a split-kl inequality. The inequality is particularly well-suited for ternary random variables, which n…

Open-Ended Question Answering

Improved Analysis of UCRL2 with Empirical Bernstein Inequality

2020-07-10 · Ronan Fruit, Matteo Pirotta, Alessandro Lazaric

We consider the problem of exploration-exploitation in communicating Markov Decision Processes. We provide an analysis of UCRL2 with Empirical Bernstein inequalities (UCRL2B). For any MDP with $S$ states, $A$ actions, $\…

Efron-Stein PAC-Bayesian Inequalities

2019-09-04 · Ilja Kuzborskij, Csaba Szepesvári

We prove semi-empirical concentration inequalities for random variables which are given as possibly nonlinear functions of independent random variables. These inequalities describe concentration of random variable in ter…

Generalization BoundsOff-policy evaluation

An Empirical Bernstein Inequality for Dependent Data in Hilbert Spaces and Applications

2025-07-10 · Erfan Mirzaei, Andreas Maurer, Vladimir R. Kostic, Massimiliano Pontil arxiv

Learning from non-independent and non-identically distributed data poses a persistent challenge in statistical learning. In this study, we introduce data-dependent Bernstein inequalities tailored for vector-valued proces…