English
Related papers

Related papers: PAC-Bayesian Policy Evaluation for Reinforcement L…

200 papers

We propose data-dependent uniform generalization bounds by approaching the problem from a PAC-Bayesian perspective. We first apply the PAC-Bayesian framework on "random sets" in a rigorous way, where the training algorithm is assumed to…

Machine Learning · Statistics 2025-02-11 Benjamin Dupuis , Paul Viallard , George Deligiannidis , Umut Simsekli

Deep learning is renowned for its theory-practice gap, whereby principled theory typically fails to provide much beneficial guidance for implementation in practice. This has been highlighted recently by the benign overfitting phenomenon:…

Machine Learning · Statistics 2023-11-14 Liam Hodgkinson , Chris van der Heide , Robert Salomone , Fred Roosta , Michael W. Mahoney

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 terms of the…

Machine Learning · Computer Science 2020-02-04 Ilja Kuzborskij , Csaba Szepesvári

This study proposes the General Bayes framework for policy learning. We consider decision problems in which a decision-maker chooses an action from an action set to maximize its expected welfare. Typical examples include treatment choice…

Machine Learning · Statistics 2026-03-02 Masahiro Kato

Bayesian inference provides a principled probabilistic framework for quantifying uncertainty by updating beliefs based on prior knowledge and observed data through Bayes' theorem. In Bayesian deep learning, neural network weights are…

Machine Learning · Computer Science 2024-10-22 Yijie Zhang

Meta-learning methods perform well on new within-distribution tasks but often fail when adapting to out-of-distribution target tasks, where transfer from source tasks can induce negative transfer. We propose a causally-aware Bayesian…

Machine Learning · Computer Science 2026-02-24 Lotta Mäkinen , Jorge Loría , Samuel Kaski

PAC-Bayes has recently re-emerged as an effective theory with which one can derive principled learning algorithms with tight performance guarantees. However, applications of PAC-Bayes to bandit problems are relatively rare, which is a great…

Machine Learning · Computer Science 2023-09-26 Hamish Flynn , David Reeb , Melih Kandemir , Jan Peters

Specification of the prior distribution for a Bayesian model is a central part of the Bayesian workflow for data analysis, but it is often difficult even for statistical experts. In principle, prior elicitation transforms domain knowledge…

This paper proposes an online tree-based Bayesian approach for reinforcement learning. For inference, we employ a generalised context tree model. This defines a distribution on multivariate Gaussian piecewise-linear models, which can be…

Machine Learning · Statistics 2014-05-05 Nikolaos Tziortziotis , Christos Dimitrakakis , Konstantinos Blekas

In this work, we propose a PAC-Bayes bound for the generalization risk of the Gibbs classifier in the multi-class classification framework. The novelty of our work is the critical use of the confusion matrix of a classifier as an error…

Machine Learning · Statistics 2013-10-23 Emilie Morvant , Sokol Koço , Liva Ralaivola

Bayesian inference allows machine learning models to express uncertainty. Current machine learning models use only a single learnable parameter combination when making predictions, and as a result are highly overconfident when their…

Machine Learning · Computer Science 2022-02-23 Andrew Wood , Moshik Hershcovitch , Daniel Waddington , Sarel Cohen , Peter Chin

Datasets are rarely a realistic approximation of the target population. Say, prevalence is misrepresented, image quality is above clinical standards, etc. This mismatch is known as sampling bias. Sampling biases are a major hindrance for…

We present two alternative ways to apply PAC-Bayesian analysis to sequences of dependent random variables. The first is based on a new lemma that enables to bound expectations of convex functions of certain dependent random variables by…

Machine Learning · Computer Science 2011-05-20 Yevgeny Seldin , François Laviolette , John Shawe-Taylor , Jan Peters , Peter Auer

Reinforcement learning (RL) for reachability specifications is fundamental in sequential decision-making, yet theoretical guarantees remain less explored. A recent work achieves asymptotic convergence to optimal policies. However, this…

Machine Learning · Computer Science 2026-05-26 Amogh Palasamudram , Jakub Svoboda , Suguman Bansal , Krishnendu Chatterjee

This paper provides a general technique for lower bounding the Bayes risk of statistical estimation, applicable to arbitrary loss functions and arbitrary prior distributions. A lower bound on the Bayes risk not only serves as a lower bound…

Statistics Theory · Mathematics 2016-12-26 Xi Chen , Adityanand Guntuboyina , Yuchen Zhang

We present a distributionally robust PAC-Bayesian framework for certifying the performance of learning-based finite-horizon controllers. While existing PAC-Bayes control literature typically assumes bounded losses and matching training and…

Machine Learning · Computer Science 2026-04-14 Domagoj Herceg , Duarte Antunes

We discuss necessary conditions for a PAC-Bayes bound to provide a meaningful generalisation guarantee. Our analysis reveals that the optimal generalisation guarantee depends solely on the distribution of the risk induced by the prior…

Machine Learning · Statistics 2025-03-12 Antoine Picard-Weibel , Eugenio Clerico , Roman Moscoviz , Benjamin Guedj

PAC-Bayes is a popular and efficient framework for obtaining generalization guarantees in situations involving uncountable hypothesis spaces. Unfortunately, in its classical formulation, it only provides guarantees on the expected risk of a…

Machine Learning · Computer Science 2025-10-30 Benjamin Leblanc , Pascal Germain

We present a modular approach to reinforcement learning that uses a Bayesian representation of the uncertainty over models. The approach, BOSS (Best of Sampled Set), drives exploration by sampling multiple models from the posterior and…

Machine Learning · Computer Science 2012-05-14 John Asmuth , Lihong Li , Michael L. Littman , Ali Nouri , David Wingate

Bayesian deep learning approaches assume model parameters to be latent random variables and infer posterior distributions to quantify uncertainty, increase safety and trust, and prevent overconfident and unpredictable behavior. However,…

Machine Learning · Computer Science 2023-07-13 Jihao Andreas Lin , Joe Watson , Pascal Klink , Jan Peters