English
Related papers

Related papers: PAC-Bayesian Reinforcement Learning Trains General…

200 papers

In recent years deep neural networks have been successfully applied to the domains of reinforcement learning \cite{bengio2009learning,krizhevsky2012imagenet,hinton2006reducing}. Deep reinforcement learning \cite{mnih2015human} is reported…

Machine Learning · Computer Science 2020-05-19 Huihui Zhang , Wu Huang

The increasing use of machine learning in safety-critical domains amplifies the risk of adversarial threats, especially data poisoning attacks that corrupt training data to degrade performance or induce unsafe behavior. Most existing…

Machine Learning · Computer Science 2026-05-13 Sara Taheri , Mahalakshmi Sabanayagam , Debarghya Ghoshdastidar , Majid Zamani

PAC-Bayesian analysis is a frequentist framework for incorporating prior knowledge into learning. It was inspired by Bayesian learning, which allows sequential data processing and naturally turns posteriors from one processing step into…

Machine Learning · Computer Science 2025-04-10 Yi-Shan Wu , Yijie Zhang , Badr-Eddine Chérief-Abdellatif , Yevgeny Seldin

Monotone learning describes learning processes in which expected performance consistently improves as the amount of training data increases. However, recent studies challenge this conventional wisdom, revealing significant gaps in the…

Machine Learning · Computer Science 2025-05-22 Ming Li , Chenyi Zhang , Qin Li

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

We study reinforcement learning (RL) with linear function approximation. Existing algorithms for this problem only have high-probability regret and/or Probably Approximately Correct (PAC) sample complexity guarantees, which cannot guarantee…

Machine Learning · Computer Science 2022-01-03 Jiafan He , Dongruo Zhou , Quanquan Gu

In this paper, we establish generalization bounds for transductive learning algorithms in the context of information theory and PAC-Bayes, covering both the random sampling and the random splitting setting. First, we show that the…

Machine Learning · Computer Science 2025-01-22 Huayi Tang , Yong Liu

We present a new family of information-theoretic generalization bounds, in which the training loss and the population loss are compared through a jointly convex function. This function is upper-bounded in terms of the disintegrated,…

Machine Learning · Computer Science 2023-03-28 Fredrik Hellström , Giuseppe Durisi

We investigate the problem of establishing finite-time probabilistic safety guarantees for discrete-time stochastic dynamical systems subject to unknown disturbance distributions, using barrier certificate methods. Our approach develops a…

Systems and Control · Electrical Eng. & Systems 2026-03-03 Taoran Wu , Dominik Wagner , C. -H. Luke Ong , Bai Xue

We consider the problem of learning rules from a data set that support a proof of a given query, under Valiant's PAC-Semantics. We show how any backward proof search algorithm that is sufficiently oblivious to the contents of its knowledge…

Artificial Intelligence · Computer Science 2019-06-25 Brendan Juba

Generalization error (also known as the out-of-sample error) measures how well the hypothesis learned from training data generalizes to previously unseen data. Proving tight generalization error bounds is a central question in statistical…

Machine Learning · Computer Science 2020-03-03 Jian Li , Xuanyuan Luo , Mingda Qiao

Conditional Value at Risk (CVaR) is a family of "coherent risk measures" which generalize the traditional mathematical expectation. Widely used in mathematical finance, it is garnering increasing interest in machine learning, e.g., as an…

Machine Learning · Computer Science 2020-11-17 Zakaria Mhammedi , Benjamin Guedj , Robert C. Williamson

We present a Bayesian view of counterfactual risk minimization (CRM) for offline learning from logged bandit feedback. Using PAC-Bayesian analysis, we derive a new generalization bound for the truncated inverse propensity score estimator.…

Machine Learning · Computer Science 2020-04-03 Ben London , Ted Sandler

A major challenge for reinforcement learning is automatically generating curricula to reduce training time or improve performance in some target task. We introduce SEBNs (Skill-Environment Bayesian Networks) which model a probabilistic…

Artificial Intelligence · Computer Science 2025-02-24 Vincent Hsiao , Mark Roberts , Laura M. Hiatt , George Konidaris , Dana Nau

We propose a novel constrained reinforcement learning method for finding optimal policies in Markov Decision Processes while satisfying temporal logic constraints with a desired probability throughout the learning process. An…

Robotics · Computer Science 2021-09-07 Derya Aksaray , Yasin Yazicioglu , Ahmet Semi Asarkaya

Critical sequential decisions are rarely single-timescale: a strategic decision causally shapes the context in which every subsequent tactical choice is made; standard bandit and reinforcement-learning theory does not capture this causal…

Artificial Intelligence · Computer Science 2026-05-29 Tim Woydt , Paul-David Zuercher

Safety is a critical component of autonomous systems and remains a challenge for learning-based policies to be utilized in the real world. In particular, policies learned using reinforcement learning often fail to generalize to novel…

Robotics · Computer Science 2023-04-04 Kai-Chieh Hsu , Allen Z. Ren , Duy Phuong Nguyen , Anirudha Majumdar , Jaime F. Fisac

This paper presents the concept of an adaptive safe padding that forces Reinforcement Learning (RL) to synthesise optimal control policies while ensuring safety during the learning process. Policies are synthesised to satisfy a goal,…

Machine Learning · Computer Science 2020-03-24 Mohammadhosein Hasanbeig , Alessandro Abate , Daniel Kroening

We study upper and lower bounds on the sample-complexity of learning near-optimal behaviour in finite-state discounted Markov Decision Processes (MDPs). For the upper bound we make the assumption that each action leads to at most two…

Machine Learning · Computer Science 2013-05-17 Tor Lattimore , Marcus Hutter

We introduce a novel technique for verification and model synthesis of sequential programs. Our technique is based on learning a regular model of the set of feasible paths in a program, and testing whether this model contains an incorrect…

Software Engineering · Computer Science 2015-11-04 Yu-Fang Chen , Chiao Hsieh , Ondřej Lengál , Tsung-Ju Lii , Ming-Hsien Tsai , Bow-Yaw Wang , Farn Wang
‹ Prev 1 8 9 10 Next ›