English
Related papers

Related papers: Beyond Time-Average Convergence: Near-Optimal Unco…

200 papers

We consider online no-regret learning in unknown games with bandit feedback, where each player can only observe its reward at each time -- determined by all players' current joint action -- rather than its gradient. We focus on the class of…

Machine Learning · Computer Science 2024-04-01 Wenjia Ba , Tianyi Lin , Jiawei Zhang , Zhengyuan Zhou

We present a new algorithm based on posterior sampling for learning in constrained Markov decision processes (CMDP) in the infinite-horizon undiscounted setting. The algorithm achieves near-optimal regret bounds while being advantageous…

Machine Learning · Computer Science 2023-09-28 Danil Provodin , Pratik Gajane , Mykola Pechenizkiy , Maurits Kaptein

We present a new online learning algorithm for cumulative discounted gain. This learning algorithm does not use exponential weights on the experts. Instead, it uses a weighting scheme that depends on the regret of the master algorithm…

Computer Science and Game Theory · Computer Science 2008-07-01 Yoav Freund , Daniel Hsu

We give a simple and computationally efficient algorithm that, for any constant $\varepsilon>0$, obtains $\varepsilon T$-swap regret within only $T = \mathsf{polylog}(n)$ rounds; this is an exponential improvement compared to the…

Computer Science and Game Theory · Computer Science 2023-11-15 Binghui Peng , Aviad Rubinstein

In this paper, online game is studied, where at each time, a group of players aim at selfishly minimizing their own time-varying cost function simultaneously subject to time-varying coupled constraints and local feasible set constraints.…

Computer Science and Game Theory · Computer Science 2023-06-29 Min Meng , Xiuxian Li , Yiguang Hong , Jie Chen , Long Wang

Learning algorithms are often used to make decisions in sequential decision-making environments. In multi-agent settings, the decisions of each agent can affect the utilities/losses of the other agents. Therefore, if an agent is good at…

Computer Science and Game Theory · Computer Science 2024-07-09 Angelos Assos , Yuval Dagan , Constantinos Daskalakis

We consider online optimization in the 1-lookahead setting, where the objective does not decompose additively over the rounds of the online game. The resulting formulation enables us to deal with non-stationary and/or long-term constraints…

Machine Learning · Statistics 2016-06-09 Rodolphe Jenatton , Jim Huang , Dominik Csiba , Cedric Archambeau

Existing Continual Learning (CL) approaches have focused on addressing catastrophic forgetting by leveraging regularization methods, replay buffers, and task-specific components. However, realistic CL solutions must be shaped not only by…

Machine Learning · Computer Science 2023-10-11 Jinyung Hong , Theodore P. Pavlic

Aligning large language models (LLMs) with human preferences has proven effective for enhancing model capabilities, yet standard preference modeling using the Bradley-Terry model assumes transitivity, overlooking the inherent complexity of…

Machine Learning · Computer Science 2026-01-05 Shulun Chen , Runlong Zhou , Zihan Zhang , Maryam Fazel , Simon S. Du

This paper introduces a dual-based algorithm framework for solving the regularized online resource allocation problems, which have potentially non-concave cumulative rewards, hard resource constraints, and a non-separable regularizer. Under…

Machine Learning · Computer Science 2023-07-18 Wanteng Ma , Ying Cao , Danny H. K. Tsang , Dong Xia

A new algorithm for regret minimization in online convex optimization is described. The regret of the algorithm after $T$ time periods is $O(\sqrt{T \log T})$ - which is the minimum possible up to a logarithmic term. In addition, the new…

Machine Learning · Computer Science 2023-07-24 Elad Hazan , Nimrod Megiddo

Bandit Convex Optimization is a fundamental class of sequential decision-making problems, where the learner selects actions from a continuous domain and observes a loss (but not its gradient) at only one point per round. We study this…

Machine Learning · Statistics 2025-12-02 Xiaoqi Liu , Dorian Baudry , Julian Zimmert , Patrick Rebeschini , Arya Akhavan

Counterfactual Regret Minimization (CFR) is an efficient no-regret learning algorithm for decision problems modeled as extensive games. CFR's regret bounds depend on the requirement of perfect recall: players always remember information…

Computer Science and Game Theory · Computer Science 2012-05-04 Marc Lanctot , Richard Gibson , Neil Burch , Martin Zinkevich , Michael Bowling

In the setting of online learning, Implicit algorithms turn out to be highly successful from a practical standpoint. However, the tightest regret analyses only show marginal improvements over Online Mirror Descent. In this work, we shed…

Machine Learning · Computer Science 2020-11-10 Nicolò Campolongo , Francesco Orabona

Learning and equilibrium computation in games are fundamental problems across computer science and economics, with applications ranging from politics to machine learning. Much of the work in this area revolves around a simple algorithm…

Computer Science and Game Theory · Computer Science 2022-07-19 Daniel Beaglehole , Max Hopkins , Daniel Kane , Sihan Liu , Shachar Lovett

The ability of intelligent agents to learn and remember multiple tasks sequentially is crucial to achieving artificial general intelligence. Many continual learning (CL) methods have been proposed to overcome catastrophic forgetting which…

Machine Learning · Computer Science 2020-09-15 Gehui Shen , Song Zhang , Xiang Chen , Zhi-Hong Deng

In learning theory, the performance of an online policy is commonly measured in terms of the static regret metric, which compares the cumulative loss of an online policy to that of an optimal benchmark in hindsight. In the definition of…

Information Theory · Computer Science 2022-08-23 Ativ Joshi , Abhishek Sinha

We address the problem of simultaneously learning and control in an online receding horizon control setting. We consider the control of an unknown linear dynamical system with general cost functions and affine constraints on the control…

Optimization and Control · Mathematics 2022-11-02 Deepan Muthirayan , Jianjun Yuan , Pramod P. Khargonekar

We study infinite-horizon average-reward constrained Markov decision processes (CMDPs) under the unichain assumption and general policy parameterizations. Existing regret analyses for constrained reinforcement learning largely rely on…

Machine Learning · Computer Science 2026-02-10 Anirudh Satheesh , Vaneet Aggarwal

We consider a generalization of the celebrated Online Convex Optimization (OCO) framework with adversarial online constraints. In this problem, an online learner interacts with an adversary sequentially over multiple rounds. At the…

Machine Learning · Computer Science 2026-01-07 Subhamon Supantha , Abhishek Sinha