English
Related papers

Related papers: How Log-Barrier Helps Exploration in Policy Optimi…

200 papers

We study the problem of learning minimax policies in zero-sum matrix games. Fiegel et al. (2025) recently showed that achieving last-iterate convergence in this setting is harder when the players are uncoupled, by proving a lower bound on…

Machine Learning · Computer Science 2026-04-17 Come Fiegel , Pierre Menard , Tadashi Kozuno , Michal Valko , Vianney Perchet

Safe exploration is a key to applying reinforcement learning (RL) in safety-critical systems. Existing safe exploration methods guaranteed safety under the assumption of regularity, and it has been difficult to apply them to large-scale…

Machine Learning · Computer Science 2021-11-10 Akifumi Wachi , Yunyue Wei , Yanan Sui

Recently, self-learning methods based on user satisfaction metrics and contextual bandits have shown promising results to enable consistent improvements in conversational AI systems. However, directly targeting such metrics by off-policy…

Machine Learning · Computer Science 2023-05-16 Mohammad Kachuee , Sungjin Lee

Online learning algorithms require to often recompute least squares regression estimates of parameters. We study improving the computational complexity of such algorithms by using stochastic gradient descent (SGD) type schemes in place of…

Machine Learning · Computer Science 2014-11-21 Nathaniel Korda , Prashanth L. A. , Rémi Munos

Stochastic zeroth-order (SZO), or gradient-free, optimization allows to optimize arbitrary functions by relying only on function evaluations under parameter perturbations, however, the iteration complexity of SZO methods suffers a factor…

Machine Learning · Statistics 2020-11-11 Artem Sokolov , Julian Hitschler , Mayumi Ohta , Stefan Riezler

The ultimate goal of a supervised learning algorithm is to produce models constructed on the training data that can generalize well to new examples. In classification, functional margin maximization -- correctly classifying as many training…

Machine Learning · Computer Science 2020-01-29 Nikolaos Nikolaou , Henry Reeve , Gavin Brown

We describe an algorithm based on a logarithmic barrier function, Newton's method, and linear conjugate gradients that obtains an approximate minimizer of a smooth function over the nonnegative orthant. We develop a bound on the complexity…

Optimization and Control · Mathematics 2019-12-05 Michael O'Neill , Stephen J. Wright

In this paper, we investigate a model-free optimal control design that minimizes an infinite horizon average expected quadratic cost of states and control actions subject to a probabilistic risk or chance constraint using input-output data.…

Systems and Control · Electrical Eng. & Systems 2024-11-11 Arunava Naha , Subhrakanti Dey

Exploration policies in Bayesian bandits maximize the average reward over problem instances drawn from some distribution $\mathcal{P}$. In this work, we learn such policies for an unknown distribution $\mathcal{P}$ using samples from…

Machine Learning · Computer Science 2020-06-11 Craig Boutilier , Chih-Wei Hsu , Branislav Kveton , Martin Mladenov , Csaba Szepesvari , Manzil Zaheer

Stochastic optimization via Stochastic Gradient Descent (SGD) is a fundamental problem in statistics and optimization. This paper revisits Stochastic Gradient Descent (SGD) for strongly convex objectives, establishing tight, uniform-in-time…

Optimization and Control · Mathematics 2026-03-19 Kang Chen , Yasong Feng , Tianyu Wang

Pure exploration in bandits formalises multiple real-world problems, such as tuning hyper-parameters or conducting user studies to test a set of items, where different safety, resource, and fairness constraints on the decision space…

Machine Learning · Computer Science 2026-02-05 Udvas Das , Debabrota Basu

Policy optimization, which finds the desired policy by maximizing value functions via optimization techniques, lies at the heart of reinforcement learning (RL). In addition to value maximization, other practical considerations arise as…

Machine Learning · Computer Science 2023-01-12 Wenhao Zhan , Shicong Cen , Baihe Huang , Yuxin Chen , Jason D. Lee , Yuejie Chi

A default assumption in the design of reinforcement-learning algorithms is that a decision-making agent always explores to learn optimal behavior. In sufficiently complex environments that approach the vastness and scale of the real world,…

Machine Learning · Computer Science 2024-07-23 Dilip Arumugam , Saurabh Kumar , Ramki Gummadi , Benjamin Van Roy

We investigate various stochastic bandit problems in the presence of adversarial corruptions. A seminal work for this problem is the BARBAR~\cite{gupta2019better} algorithm, which achieves both robustness and efficiency. However, it suffers…

Machine Learning · Computer Science 2026-01-05 Zicheng Hu , Cheng Chen

Despite the significant potential for various applications, stochastic games with long-run average payoffs have received limited scholarly attention, particularly concerning the development of learning algorithms for them due to the…

Computer Science and Game Theory · Computer Science 2024-05-17 Junyue Zhang , Yifen Mu

The problem of synthesizing stochastic explicit model predictive control policies is known to be quickly intractable even for systems of modest complexity when using classical control-theoretic methods. To address this challenge, we present…

Machine Learning · Computer Science 2022-05-24 Ján Drgoňa , Sayak Mukherjee , Aaron Tuor , Mahantesh Halappanavar , Draguna Vrabie

We study post-training linear autoregressive models with outcome and process rewards. Given a context $\boldsymbol{x}$, the model must predict the response $\boldsymbol{y} \in Y^N$, a sequence of length $N$ that satisfies a $\gamma$ margin…

Machine Learning · Statistics 2026-03-10 Alireza Mousavi-Hosseini , Murat A. Erdogdu

We study the finite-horizon Restless Multi-Armed Bandit (RMAB) problem with $N$ homogeneous arms. Prior work has shown that when an RMAB satisfies a non-degeneracy condition, Linear-Programming-based (LP-based) policies derived from the…

Optimization and Control · Mathematics 2025-05-27 Chen Yan , Weina Wang , Lei Ying

Machine learning models trained with \emph{stochastic} gradient descent (SGD) can generalize better than those trained with deterministic gradient descent (GD). In this work, we study SGD's impact on generalization through the lens of the…

Machine Learning · Computer Science 2025-12-09 Hongjian Lan , Yucong Liu , Florian Schäfer

We study realizable continual linear regression under random task orderings, a common setting for developing continual learning theory. In this setup, the worst-case expected loss after $k$ learning iterations admits a lower bound of…

Machine Learning · Computer Science 2025-10-28 Ran Levinstein , Amit Attia , Matan Schliserman , Uri Sherman , Tomer Koren , Daniel Soudry , Itay Evron
‹ Prev 1 4 5 6 7 8 10 Next ›