English
Related papers

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

200 papers

Aggregated predictors are obtained by making a set of basic predictors vote according to some weights, that is, to some probability distribution. Randomized predictors are obtained by sampling in a set of basic predictors, according to some…

Machine Learning · Statistics 2025-03-03 Pierre Alquier

Existing guarantees in terms of rigorous upper bounds on the generalization error for the original random forest algorithm, one of the most frequently used machine learning methods, are unsatisfying. We discuss and evaluate various…

Machine Learning · Computer Science 2019-03-07 Stephan Sloth Lorenzen , Christian Igel , Yevgeny Seldin

PAC-Bayesian is an analysis framework where the training error can be expressed as the weighted average of the hypotheses in the posterior distribution whilst incorporating the prior knowledge. In addition to being a pure generalization…

Machine Learning · Computer Science 2022-02-07 Wei Huang , Chunrui Liu , Yilan Chen , Tianyu Liu , Richard Yi Da Xu

The Probably Approximately Correct (PAC) Bayes framework (McAllester, 1999) can incorporate knowledge about the learning algorithm and (data) distribution through the use of distribution-dependent priors, yielding tighter generalization…

Machine Learning · Computer Science 2019-04-22 Gintare Karolina Dziugaite , Daniel M. Roy

Meta-Learning aims to speed up the learning process on new tasks by acquiring useful inductive biases from datasets of related learning tasks. While, in practice, the number of related tasks available is often small, most of the existing…

Machine Learning · Statistics 2023-12-27 Jonas Rothfuss , Martin Josifoski , Vincent Fortuin , Andreas Krause

In this paper the problem of learning appropriate bias for an environment of related tasks is examined from a Bayesian perspective. The environment of related tasks is shown to be naturally modelled by the concept of an {\em objective}…

Machine Learning · Computer Science 2019-11-15 Jonathan Baxter

In the Bayesian approach to sequential decision making, exact calculation of the (subjective) utility is intractable. This extends to most special cases of interest, such as reinforcement learning problems. While utility bounds are known to…

Machine Learning · Computer Science 2011-11-14 Christos Dimitrakakis

PAC-Bayesian bounds are known to be tight and informative when studying the generalization ability of randomized classifiers. However, they require a loose and costly derandomization step when applied to some families of deterministic…

Machine Learning · Statistics 2023-09-19 Paul Viallard , Pascal Germain , Amaury Habrard , Emilie Morvant

We use the PAC-Bayesian theory for 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-Bayesian bounds) and explicit…

Machine Learning · Computer Science 2025-02-26 Michael Sucker , Jalal Fadili , Peter Ochs

Meta-learning can successfully acquire useful inductive biases from data. Yet, its generalization properties to unseen learning tasks are poorly understood. Particularly if the number of meta-training tasks is small, this raises concerns…

Machine Learning · Statistics 2021-06-21 Jonas Rothfuss , Vincent Fortuin , Martin Josifoski , Andreas Krause

Lifelong reinforcement learning (RL) has been developed as a paradigm for extending single-task RL to more realistic, dynamic settings. In lifelong RL, the "life" of an RL agent is modeled as a stream of tasks drawn from a task…

Bayesian methods for machine learning have been widely investigated, yielding principled methods for incorporating prior information into inference algorithms. In this survey, we provide an in-depth review of the role of Bayesian methods…

Artificial Intelligence · Computer Science 2016-09-16 Mohammad Ghavamzadeh , Shie Mannor , Joelle Pineau , Aviv Tamar

This paper introduces a simple, general framework for likelihood-free Bayesian reinforcement learning, through Approximate Bayesian Computation (ABC). The main advantage is that we only require a prior distribution on a class of simulators…

Machine Learning · Statistics 2013-07-01 Christos Dimitrakakis , Nikolaos Tziortziotis

The Bayesian posterior minimizes the "inferential risk" which itself bounds the "predictive risk". This bound is tight when the likelihood and prior are well-specified. However since misspecification induces a gap, the Bayesian posterior…

Machine Learning · Computer Science 2022-05-24 Warren R. Morningstar , Alexander A. Alemi , Joshua V. Dillon

Some machine learning applications require continual learning - where data comes in a sequence of datasets, each is used for training and then permanently discarded. From a Bayesian perspective, continual learning seems straightforward:…

Machine Learning · Statistics 2019-02-19 Sebastian Farquhar , Yarin Gal

As AI systems become increasingly autonomous, reliably aligning their decision-making with human preferences is essential. Inverse reinforcement learning (IRL) offers a promising approach to infer preferences from demonstrations. These…

Machine Learning · Computer Science 2025-09-22 Ondrej Bajgar , Dewi S. W. Gould , Jonathon Liu , Alessandro Abate , Konstantinos Gatsis , Michael A. Osborne

In meta reinforcement learning (meta RL), an agent learns from a set of training tasks how to quickly solve a new task, drawn from the same task distribution. The optimal meta RL policy, a.k.a. the Bayes-optimal behavior, is well defined,…

Machine Learning · Computer Science 2024-04-01 Zohar Rimon , Aviv Tamar , Gilad Adler

PAC-Bayesian bounds have proven to be a valuable tool for deriving generalization bounds and for designing new learning algorithms in machine learning. However, it typically focus on providing generalization bounds with respect to a chosen…

Machine Learning · Statistics 2024-08-19 The Tien Mai

Meta-reinforcement learning trains a single reinforcement learning agent on a distribution of tasks to quickly generalize to new tasks outside of the training set at test time. From a Bayesian perspective, one can interpret this as…

Machine Learning · Computer Science 2025-11-20 Joery A. de Vries , Jinke He , Mathijs M. de Weerdt , Matthijs T. J. Spaan

Classical PAC generalization bounds on the prediction risk of a classifier are insufficient to provide theoretical guarantees on fairness when the goal is to learn models balancing predictive risk and fairness constraints. We propose a…