English
Related papers

Related papers: Accelerating Value Iteration with Anchoring

200 papers

We study stochastic convex optimization subjected to linear equality constraints. Traditional Stochastic Alternating Direction Method of Multipliers and its Nesterov's acceleration scheme can only achieve ergodic O(1/\sqrt{K}) convergence…

Optimization and Control · Mathematics 2017-04-25 Cong Fang , Feng Cheng , Zhouchen Lin

Variational inference (VI) is a specific type of approximate Bayesian inference that approximates an intractable posterior distribution with a tractable one. VI casts the inference problem as an optimization problem, more specifically, the…

Machine Learning · Computer Science 2022-12-20 Felix Leibfried

Optimizing the learning rate remains a critical challenge in machine learning, essential for achieving model stability and efficient convergence. The Vector Auxiliary Variable (VAV) algorithm introduces a novel energy-based self-adjustable…

Machine Learning · Computer Science 2024-11-12 Jiahao Zhang , Christian Moya , Guang Lin

We develop an interior-point approach to solve constrained variational inequality (cVI) problems. Inspired by the efficacy of the alternating direction method of multipliers (ADMM) method in the single-objective context, we generalize ADMM…

Machine Learning · Statistics 2023-03-07 Tong Yang , Michael I. Jordan , Tatjana Chavdarova

Solving stochastic games with the reachability objective is a fundamental problem, especially in quantitative verification and synthesis. For this purpose, bounded value iteration (BVI) attracts attention as an efficient iterative method.…

Logic in Computer Science · Computer Science 2020-09-21 Kittiphon Phalakarn , Toru Takisaka , Thomas Haas , Ichiro Hasuo

Since their introduction, anchoring methods in extragradient-type saddlepoint problems have inspired a flurry of research due to their ability to provide order-optimal rates of accelerated convergence in very general problem settings. Such…

Optimization and Control · Mathematics 2025-06-10 James Alcala , Yat Tin Chow , Mahesh Sunkula

Tail-end risk measures such as static conditional value-at-risk (CVaR) are used in safety-critical applications to prevent rare, yet catastrophic events. Unlike risk-neutral objectives, the static CVaR of the return depends on entire…

Machine Learning · Computer Science 2026-02-04 Aneri Muni , Vincent Taboga , Esther Derman , Pierre-Luc Bacon , Erick Delage

We study the general approach to accelerating the convergence of the most widely used solution method of Markov decision processes with the total expected discounted reward. Inspired by the monotone behavior of the contraction mappings in…

Optimization and Control · Mathematics 2008-03-28 Oleksandr Shlakhter , Chi-Guhn Lee , Dmitry Khmelev , Nasser Jaber

This paper revisits the recently proposed reward centering algorithms including simple reward centering (SRC) and value-based reward centering (VRC), and points out that SRC is indeed the reward centering, while VRC is essentially Bellman…

Machine Learning · Computer Science 2025-02-06 Xingguo Chen , Yu Gong , Shangdong Yang , Wenhao Wang

This paper applies the authors' recent results on asynchronous stochastic approximation (SA) in the Borkar-Meyn framework to reinforcement learning in average-reward semi-Markov decision processes (SMDPs). We establish the convergence of an…

Machine Learning · Computer Science 2025-12-09 Huizhen Yu , Yi Wan , Richard S. Sutton

Advantage Learning (AL) seeks to increase the action gap between the optimal action and its competitors, so as to improve the robustness to estimation errors. However, the method becomes problematic when the optimal action induced by the…

Machine Learning · Computer Science 2022-03-23 Zhe Zhang , Yaozhong Gan , Xiaoyang Tan

Critic-free reinforcement learning methods, particularly group policies, have attracted considerable attention for their efficiency in complex tasks. However, these methods rely heavily on multiple sampling and comparisons within the policy…

Machine Learning · Computer Science 2025-09-22 Wenfeng Feng , Penghong Zhao , Guochao Jiang , Chuzhan Hao , Yuewei Zhang , Guohua Liu , Hao Wang

One of the most widely used methods for solving average cost MDP problems is the value iteration method. This method, however, is often computationally impractical and restricted in size of solvable MDP problems. We propose acceleration…

Optimization and Control · Mathematics 2008-06-03 Oleksandr Shlakhter , Chi-Guhn Lee

One of the most natural approaches to reinforcement learning (RL) with function approximation is value iteration, which inductively generates approximations to the optimal value function by solving a sequence of regression problems. To…

Machine Learning · Computer Science 2024-06-19 Noah Golowich , Ankur Moitra

Nesterov's accelerated gradient methods (AGM) have been successfully applied in many machine learning areas. However, their empirical performance on training max-margin models has been inferior to existing specialized solvers. In this…

Machine Learning · Computer Science 2010-11-03 Xinhua Zhang , Ankan Saha , S. V. N. Vishwanathan

Boosting is one of the most significant advances in machine learning for classification and regression. In its original and computationally flexible version, boosting seeks to minimize empirically a loss function in a greedy fashion. The…

Statistics Theory · Mathematics 2007-06-13 Tong Zhang , Bin Yu

Variational inference (VI) provides fast approximations of a Bayesian posterior in part because it formulates posterior approximation as an optimization problem: to find the closest distribution to the exact posterior over some family of…

Machine Learning · Statistics 2017-03-03 Fangjian Guo , Xiangyu Wang , Kai Fan , Tamara Broderick , David B. Dunson

Value iteration is a fixed point iteration technique utilized to obtain the optimal value function and policy in a discounted reward Markov Decision Process (MDP). Here, a contraction operator is constructed and applied repeatedly to arrive…

Machine Learning · Computer Science 2021-09-21 Chandramouli Kamanchi , Raghuram Bharadwaj Diddigi , Shalabh Bhatnagar

We consider the problem of learning the optimal action-value function in the discounted-reward Markov decision processes (MDPs). We prove a new PAC bound on the sample-complexity of model-based value iteration algorithm in the presence of…

Machine Learning · Computer Science 2012-07-03 Mohammad Gheshlaghi Azar , Remi Munos , Bert Kappen

The Vector AutoRegressive Moving Average (VARMA) model is fundamental to the theory of multivariate time series; however, identifiability issues have led practitioners to abandon it in favor of the simpler but more restrictive Vector…

Methodology · Statistics 2021-06-09 Ines Wilms , Sumanta Basu , Jacob Bien , David S. Matteson