English
Related papers

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

200 papers

While the Bayesian decision-theoretic framework offers an elegant solution to the problem of decision making under uncertainty, one question is how to appropriately select the prior distribution. One idea is to employ a worst-case prior.…

Machine Learning · Computer Science 2023-02-22 Thomas Kleine Buening , Christos Dimitrakakis , Hannes Eriksson , Divya Grover , Emilio Jorge

We derive a novel PAC-Bayesian generalization bound for reinforcement learning that explicitly accounts for Markov dependencies in the data, through the chain's mixing time. This contributes to overcoming challenges in obtaining…

Machine Learning · Computer Science 2026-02-10 Abdelkrim Zitouni , Mehdi Hennequin , Juba Agoun , Ryan Horache , Nadia Kabachi , Omar Rivasplata

By leveraging experience from previous tasks, meta-learning algorithms can achieve effective fast adaptation ability when encountering new tasks. However it is unclear how the generalization property applies to new tasks. Probably…

Machine Learning · Computer Science 2021-02-09 Tianyu Liu , Jie Lu , Zheng Yan , Guangquan Zhang

In the field of reinforcement learning there has been recent progress towards safety and high-confidence bounds on policy performance. However, to our knowledge, no practical methods exist for determining high-confidence policy performance…

Artificial Intelligence · Computer Science 2018-06-26 Daniel S. Brown , Scott Niekum

We propose a probabilistic framework to directly insert prior knowledge in reinforcement learning (RL) algorithms by defining the behaviour policy as a Bayesian posterior distribution. Such a posterior combines task specific information…

Machine Learning · Computer Science 2018-10-02 Michalis K. Titsias , Sotirios Nikoloutsopoulos

Most PAC-Bayesian bounds hold in the batch learning setting where data is collected at once, prior to inference or prediction. This somewhat departs from many contemporary learning problems where data streams are collected and the…

Machine Learning · Computer Science 2023-01-25 Maxime Haddouche , Benjamin Guedj

Multiclass neural networks are a common tool in modern unsupervised domain adaptation, yet an appropriate theoretical description for their non-uniform sample complexity is lacking in the adaptation literature. To fill this gap, we propose…

Machine Learning · Computer Science 2022-07-13 Anthony Sicilia , Katherine Atwell , Malihe Alikhani , Seong Jae Hwang

Transfer learning has received a lot of attention in the machine learning community over the last years, and several effective algorithms have been developed. However, relatively little is known about their theoretical properties,…

Machine Learning · Statistics 2014-05-13 Anastasia Pentina , Christoph H. Lampert

We introduce a new framework for studying meta-learning methods using PAC-Bayesian theory. Its main advantage over previous work is that it allows for more flexibility in how the transfer of knowledge between tasks is realized. For previous…

Machine Learning · Computer Science 2024-05-30 Hossein Zakerinia , Amin Behjati , Christoph H. Lampert

The PAC-Bayesian framework has significantly advanced the understanding of statistical learning, particularly for majority voting methods. Despite its successes, its application to multi-view learning -- a setting with multiple…

Machine Learning · Computer Science 2025-10-15 Mehdi Hennequin , Abdelkrim Zitouni , Khalid Benabdeslem , Haytham Elghazel , Yacine Gaci

We apply the PAC-Bayes theory to the setting of learning-to-optimize. To the best of our knowledge, we present the first framework to learn optimization algorithms with provable generalization guarantees (PAC-bounds) and explicit trade-off…

Machine Learning · Computer Science 2023-02-16 Michael Sucker , Peter Ochs

Previous research on PAC-Bayes learning theory has focused extensively on establishing tight upper bounds for test errors. A recently proposed training procedure called PAC-Bayes training, updates the model toward minimizing these bounds.…

Machine Learning · Statistics 2024-10-22 Xitong Zhang , Avrajit Ghosh , Guangliang Liu , Rongrong Wang

We study the issue of PAC-Bayesian domain adaptation: We want to learn, from a source domain, a majority vote model dedicated to a target one. Our theoretical contribution brings a new perspective by deriving an upper-bound on the target…

Machine Learning · Statistics 2016-07-27 Pascal Germain , Amaury Habrard , François Laviolette , Emilie Morvant

We focus on a stochastic learning model where the learner observes a finite set of training examples and the output of the learning process is a data-dependent distribution over a space of hypotheses. The learned data-dependent distribution…

Machine Learning · Statistics 2020-12-29 Omar Rivasplata , Ilja Kuzborskij , Csaba Szepesvari , John Shawe-Taylor

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, but related, target distribution. Firstly, we…

Machine Learning · Statistics 2019-11-19 Pascal Germain , Amaury Habrard , François Laviolette , Emilie Morvant

PAC-Bayes is a useful framework for deriving generalization bounds which was introduced by McAllester ('98). This framework has the flexibility of deriving distribution- and algorithm-dependent bounds, which are often tighter than…

Machine Learning · Computer Science 2021-09-06 Roi Livni , Shay Moran

In meta-learning an agent extracts knowledge from observed tasks, aiming to facilitate learning of novel future tasks. Under the assumption that future tasks are 'related' to previous tasks, the accumulated knowledge should be learned in a…

Machine Learning · Statistics 2019-05-21 Ron Amit , Ron Meir

Recent works have investigated deep learning models trained by optimising PAC-Bayes bounds, with priors that are learnt on subsets of the data. This combination has been shown to lead not only to accurate classifiers, but also to remarkably…

Control policies from imitation learning can often fail to generalize to novel environments due to imperfect demonstrations or the inability of imitation learning algorithms to accurately infer the expert's policies. In this paper, we…

Robotics · Computer Science 2020-12-04 Allen Z. Ren , Sushant Veer , Anirudha Majumdar

This paper presents eight PAC-Bayes bounds to analyze the generalization performance of multi-view classifiers. These bounds adopt data dependent Gaussian priors which emphasize classifiers with high view agreements. The center of the prior…

Machine Learning · Computer Science 2016-06-07 Shiliang Sun , John Shawe-Taylor , Liang Mao
‹ Prev 1 2 3 10 Next ›