English
Related papers

Related papers: Operator Splitting Value Iteration

200 papers

In this work, we address a class of nonconvex nonsmooth optimization problems where the objective function is the sum of two smooth functions (one of which is proximable) and two nonsmooth functions (one proper, closed and proximable, and…

Optimization and Control · Mathematics 2025-03-26 Jan Harold Alcantara , Ching-pei Lee , Akiko Takeda

On the basis of additive schemes (splitting schemes) we construct efficient numerical algorithms to solve approximately the initial-boundary value problems for systems of time-dependent partial differential equations (PDEs). In many applied…

Numerical Analysis · Computer Science 2011-12-07 Petr N. Vabishchevich

Large-scale deep learning models contribute to significant performance improvements on varieties of downstream tasks. Current data and model parallelism approaches utilize model replication and partition techniques to support the…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-05-22 Youhe Jiang , Fangcheng Fu , Xupeng Miao , Xiaonan Nie , Bin Cui

This study explores distributed optimization problems with clique-wise coupling via operator splitting and how we can utilize this framework for performance analysis and enhancement. This framework extends beyond conventional pairwise…

Optimization and Control · Mathematics 2025-06-24 Yuto Watanabe , Kazunori Sakurama

Value iteration-type methods have been extensively studied for computing a nearly optimal value function in reinforcement learning (RL). Under a generative sampling model, these methods can achieve sharper sample complexity than policy…

Optimization and Control · Mathematics 2026-04-08 Zhichao Jia , Guanghui Lan

We propose and analyze an adaptive step-size variant of the Davis-Yin three operator splitting. This method can solve optimization problems composed by a sum of a smooth term for which we have access to its gradient and an arbitrary number…

Optimization and Control · Mathematics 2018-08-02 Fabian Pedregosa , Gauthier Gidel

This paper proposes a method for designing diagonal preconditioners for a preconditioned primal-dual splitting method (P-PDS), an efficient algorithm that solves nonsmooth convex optimization problems. To speed up the convergence of P-PDS,…

Signal Processing · Electrical Eng. & Systems 2023-07-25 Kazuki Naganuma , Shunsuke Ono

Long-horizon tasks, which have a large discount factor, pose a challenge for most conventional reinforcement learning (RL) algorithms. Algorithms such as Value Iteration and Temporal Difference (TD) learning have a slow convergence rate and…

Machine Learning · Computer Science 2024-09-04 Mark Bedaywi , Amin Rakhsha , Amir-massoud Farahmand

Temporal difference learning and Residual Gradient methods are the most widely used temporal difference based learning algorithms; however, it has been shown that none of their objective functions is optimal w.r.t approximating the true…

Machine Learning · Computer Science 2017-04-21 Bo Liu , Daoming Lyu , Wen Dong , Saad Biaz

Algorithmic analysis of Markov decision processes (MDP) and stochastic games (SG) in practice relies on value-iteration (VI) algorithms. Since basic VI does not provide guarantees on the precision of the result, variants of VI have been…

Computer Science and Game Theory · Computer Science 2025-09-18 Muqsit Azeem , Jan Kretinsky , Maximilian Weininger

Algorithmic analysis of Markov decision processes (MDP) and stochastic games (SG) in practice relies on value-iteration (VI) algorithms. Since the basic version of VI does not provide guarantees on the precision of the result, variants of…

Computer Science and Game Theory · Computer Science 2026-03-31 Muqsit Azeem , Jan Kretinsky , Maximilian Weininger

We present a technique for speeding up the convergence of value iteration for partially observable Markov decisions processes (POMDPs). The underlying idea is similar to that behind modified policy iteration for fully observable Markov…

Artificial Intelligence · Computer Science 2013-01-30 Nevin Lianwen Zhang , Stephen S. Lee , Weihong Zhang

Real-life machine learning problems exhibit distributional shifts in the data from one time to another or from one place to another. This behavior is beyond the scope of the traditional empirical risk minimization paradigm, which assumes…

Machine Learning · Computer Science 2024-07-24 Timothy DeLise

Euler's elastica model has a wide range of applications in Image Processing and Computer Vision. However, the non-convexity, the non-smoothness and the nonlinearity of the associated energy functional make its minimization a challenging…

Numerical Analysis · Mathematics 2020-01-10 Liang-Jian Deng , Roland Glowinski , Xue-Cheng Tai

The fundamental computational issues in Bayesian inverse problems (BIP) governed by partial differential equations (PDEs) stem from the requirement of repeated forward model evaluations. A popular strategy to reduce such costs is to replace…

Numerical Analysis · Mathematics 2024-09-05 Zhiwei Gao , Liang Yan , Tao Zhou

We study reinforcement learning in infinite-horizon average-reward settings with linear MDPs. Previous work addresses this problem by approximating the average-reward setting by discounted setting and employing a value iteration-based…

Machine Learning · Computer Science 2025-04-17 Kihyuk Hong , Ambuj Tewari

In this paper we consider infinite horizon discounted dynamic programming problems with finite state and control spaces, and partial state observations. We discuss an algorithm that uses multistep lookahead, truncated rollout with a known…

Robotics · Computer Science 2020-02-12 Sushmita Bhattacharya , Sahil Badyal , Thomas Wheeler , Stephanie Gil , Dimitri Bertsekas

Analyzing the worst-case performance of deep neural networks against input perturbations amounts to solving a large-scale non-convex optimization problem, for which several past works have proposed convex relaxations as a promising…

Machine Learning · Computer Science 2022-07-11 Shaoru Chen , Eric Wong , J. Zico Kolter , Mahyar Fazlyab

Partially observable Markov decision processes (POMDPs) provide an elegant mathematical framework for modeling complex decision and planning problems in stochastic domains in which states of the system are observable only indirectly, via a…

Artificial Intelligence · Computer Science 2011-06-02 M. Hauskrecht

Value Iteration Networks (VINs) have emerged as a popular method to incorporate planning algorithms within deep reinforcement learning, enabling performance improvements on tasks requiring long-range reasoning and understanding of…

Machine Learning · Computer Science 2020-12-08 Andreea Deac , Petar Veličković , Ognjen Milinković , Pierre-Luc Bacon , Jian Tang , Mladen Nikolić