English
Related papers

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

200 papers

In this paper, we provide two main contributions in PAC-Bayesian theory for domain adaptation where the objective is to learn, from a source distribution, a well-performing majority vote on a different target distribution. On the one hand,…

Machine Learning · Statistics 2016-08-10 Pascal Germain , Amaury Habrard , François Laviolette , Emilie Morvant

The behavior of many Bayesian models used in machine learning critically depends on the choice of prior distributions, controlled by some hyperparameters that are typically selected by Bayesian optimization or cross-validation. This…

Machine Learning · Statistics 2023-10-09 Eliezer de Souza da Silva , Tomasz Kuśmierczyk , Marcelo Hartmann , Arto Klami

When utilising PAC-Bayes theory for risk certification, it is usually necessary to estimate and bound the Gibbs risk of the PAC-Bayes posterior. Many works in the literature employ a method for this which requires a large number of passes…

Machine Learning · Computer Science 2022-10-21 Felix Biggs

This work advances randomized exploration in reinforcement learning (RL) with function approximation modeled by linear mixture MDPs. We establish the first prior-dependent Bayesian regret bound for RL with function approximation; and refine…

Machine Learning · Statistics 2024-03-19 Yingru Li , Zhi-Quan Luo

Meta learning automatically infers an inductive bias, that includes the hyperparameter of the base-learning algorithm, by observing data from a finite number of related tasks. This paper studies PAC-Bayes bounds on meta generalization gap.…

Machine Learning · Computer Science 2022-06-14 Arezou Rezazadeh

When I first encountered PAC-Bayesian concentration inequalities they seemed to me to be rather disconnected from good old-fashioned results like Hoeffding's and Bernstein's inequalities. But, at least for one flavour of the PAC-Bayesian…

Machine Learning · Statistics 2014-05-08 Tim van Erven

This paper provides a statistical analysis of high-dimensional batch Reinforcement Learning (RL) using sparse linear function approximation. When there is a large number of candidate features, our result sheds light on the fact that…

Machine Learning · Computer Science 2020-11-10 Botao Hao , Yaqi Duan , Tor Lattimore , Csaba Szepesvári , Mengdi Wang

We propose a novel method for closed-form predictive distribution modeling with neural nets. In quantifying prediction uncertainty, we build on Evidential Deep Learning, which has been impactful as being both simple to implement and giving…

Machine Learning · Statistics 2021-01-22 Manuel Haussmann , Sebastian Gerwinn , Melih Kandemir

Learning a sequence of tasks without access to i.i.d. observations is a widely studied form of continual learning (CL) that remains challenging. In principle, Bayesian learning directly applies to this setting, since recursive and one-off…

This paper presents an approach for learning vision-based planners that provably generalize to novel environments (i.e., environments unseen during training). We leverage the Probably Approximately Correct (PAC)-Bayes framework to obtain an…

Robotics · Computer Science 2020-11-11 Sushant Veer , Anirudha Majumdar

We revisit Rahimi and Recht (2007)'s kernel random Fourier features (RFF) method through the lens of the PAC-Bayesian theory. While the primary goal of RFF is to approximate a kernel, we look at the Fourier transform as a prior distribution…

Machine Learning · Statistics 2019-03-28 Gaël Letarte , Emilie Morvant , Pascal Germain

Transfer learning is a machine learning paradigm where knowledge from one problem is utilized to solve a new but related problem. While conceivable that knowledge from one task could be useful for solving a related task, if not executed…

Machine Learning · Computer Science 2021-10-01 Xuetong Wu , Jonathan H. Manton , Uwe Aickelin , Jingge Zhu

Bayesian statistics has gained popularity in psychological research due to its intuitive uncertainty quantification and convenient information-updating rules. In many applications, however, prior distributions are introduced merely as…

Methodology · Statistics 2026-03-10 Yang Liu , Jonathan P. Williams , Jan Hannig

In this paper we derive a Probably Approxilmately Correct(PAC)-Bayesian error bound for linear time-invariant (LTI) stochastic dynamical systems with inputs. Such bounds are widespread in machine learning, and they are useful for…

Machine Learning · Statistics 2023-03-30 Deividas Eringis , John Leth , Zheng-Hua Tan , Rafael Wisniewski , Mihaly Petreczky

PAC-Bayesian learning bounds are of the utmost interest to the learning community. Their role is to connect the generalization ability of an aggregation distribution $\rho$ to its empirical risk and to its Kullback-Leibler divergence with…

Machine Learning · Statistics 2019-05-24 Pierre Alquier , Benjamin Guedj

Bayesian reinforcement learning (BRL) is a method that merges principles from Bayesian statistics and reinforcement learning to make optimal decisions in uncertain environments. As a model-based RL method, it has two key components: (1)…

Machine Learning · Statistics 2025-06-03 Shreya Sinha Roy , Richard G. Everitt , Christian P. Robert , Ritabrata Dutta

We develop a unified Data Processing Inequality PAC-Bayesian framework -- abbreviated DPI-PAC-Bayesian -- for deriving generalization error bounds in the supervised learning setting. By embedding the Data Processing Inequality (DPI) into…

Information Theory · Computer Science 2025-08-26 Muhan Guan , Farhad Farokhi , Jingge Zhu

Despite success in many challenging problems, reinforcement learning (RL) is still confronted with sample inefficiency, which can be mitigated by introducing prior knowledge to agents. However, many transfer techniques in reinforcement…

Machine Learning · Computer Science 2022-09-21 Matheus Centa , Philippe Preux

In this paper we study a model-based approach to calculating approximately optimal policies in Markovian Decision Processes. In particular, we derive novel bounds on the loss of using a policy derived from a factored linear model, a class…

Machine Learning · Statistics 2016-09-22 Bernardo Ávila Pires , Csaba Szepesvári

We derive PAC-Bayesian learning guarantees for heavy-tailed losses, and obtain a novel optimal Gibbs posterior which enjoys finite-sample excess risk bounds at logarithmic confidence. Our core technique itself makes use of PAC-Bayesian…

Machine Learning · Statistics 2019-12-19 Matthew J. Holland
‹ Prev 1 4 5 6 7 8 10 Next ›