English
Related papers

Related papers: Proximal Algorithms and Temporal Differences for L…

200 papers

Value functions derived from Markov decision processes arise as a central component of algorithms as well as performance metrics in many statistics and engineering applications of machine learning techniques. Computation of the solution to…

Machine Learning · Computer Science 2020-03-02 Adithya M. Devraj , Ioannis Kontoyiannis , Sean P. Meyn

In this paper, we focus on the relaxed proximal point algorithm (RPPA) for solving convex (possibly nonsmooth) optimization problems. We conduct a comprehensive study on three types of relaxation schedules: (i) constant schedule with…

Optimization and Control · Mathematics 2024-10-14 Bofan Wang , Shiqian Ma , Junfeng Yang , Danqing Zhou

We investigate a family of approximate multi-step proximal point methods, framed as implicit linear discretizations of gradient flow. The resulting methods are multi-step proximal point methods, with similar computational cost in each…

Optimization and Control · Mathematics 2025-01-15 Yushen Huang , Yifan Sun

We consider a regularized least squares problem, with regularization by structured sparsity-inducing norms, which extend the usual $\ell_1$ and the group lasso penalty, by allowing the subsets to overlap. Such regularizations lead to…

Optimization and Control · Mathematics 2012-09-04 Silvia Villa , Lorenzo Rosasco , Sofia Mosci , Alessandro Verri

We introduce a new sequential subspace optimization method for large-scale saddle-point problems. It solves iteratively a sequence of auxiliary saddle-point problems in low-dimensional subspaces, spanned by directions derived from…

Optimization and Control · Mathematics 2020-08-24 Yoni Choukroun , Michael Zibulevsky , Pavel Kisilev

In this paper, we analyze the convergence rate of the gradient temporal difference learning (GTD) family of algorithms. Previous analyses of this class of algorithms use ODE techniques to prove asymptotic convergence, and to the best of our…

Machine Learning · Computer Science 2020-07-06 Bo Liu , Ji Liu , Mohammad Ghavamzadeh , Sridhar Mahadevan , Marek Petrik

This paper considers an optimization problem for a dynamical system whose evolution depends on a collection of binary decision variables. We develop scalable approximation algorithms with provable suboptimality bounds to provide…

Optimization and Control · Mathematics 2016-10-31 Insoon Yang , Samuel A. Burden , Ram Rajagopal , S. Shankar Sastry , Claire J. Tomlin

In this paper we consider the problem of obtaining sharp bounds for the performance of temporal difference (TD) methods with linear function approximation for policy evaluation in discounted Markov decision processes. We show that a simple…

Machine Learning · Statistics 2024-06-18 Sergey Samsonov , Daniil Tiapkin , Alexey Naumov , Eric Moulines

This paper proposes a novel proximal-gradient algorithm for a decentralized optimization problem with a composite objective containing smooth and non-smooth terms. Specifically, the smooth and nonsmooth terms are dealt with by gradient and…

Optimization and Control · Mathematics 2021-02-02 Zhi Li , Wei Shi , Ming Yan

Recurrent neural networks are widely used in speech and language processing. Due to dependency on the past, standard algorithms for training these models, such as back-propagation through time (BPTT), cannot be efficiently parallelised.…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-07 Zhengxiong Wang , Anton Ragni

We propose a new modified primal-dual proximal best approximation method for solving convex not necessarily differentiable optimization problems. The novelty of the method relies on introducing memory by taking into account iterates…

Optimization and Control · Mathematics 2018-04-18 Ewa M. Bednarczuk , Anna Jezierska , Krzysztof E. Rutkowski

This paper presents fast first-order methods for solving linear programs (LPs) approximately. We adapt online linear programming algorithms to offline LPs and obtain algorithms that avoid any matrix multiplication. We also introduce a…

Optimization and Control · Mathematics 2024-11-07 Wenzhi Gao , Dongdong Ge , Chunlin Sun , Yinyu Ye

We describe an efficient implementation of a recent simplex-type algorithm for the exact solution of separated continuous linear programs, and compare it with linear programming approximation of these problems obtained via discretization of…

Optimization and Control · Mathematics 2021-10-07 Evgeny Shindin , Michael Masin , Gideon Weiss , Alexander Zadorojniy

The need for fast sparse optimization is emerging, e.g., to deal with large-dimensional data-driven problems and to track time-varying systems. In the framework of linear sparse optimization, the iterative shrinkage-thresholding algorithm…

Optimization and Control · Mathematics 2025-01-22 Vito Cerone , Sophie M. Fosson , Diego Regruto

As supported by abundant experimental evidence, neural networks are state-of-the-art for many approximation tasks in high-dimensional spaces. Still, there is a lack of a rigorous theoretical understanding of what they can approximate, at…

Numerical Analysis · Mathematics 2024-06-24 Elena Celledoni , James Jackaman , Davide Murari , Brynjulf Owren

Fixed-parameter algorithms, approximation algorithms and moderately exponential algorithms are three major approaches to algorithms design. While each of them being very active in its own, there is an increasing attention to the connection…

Computational Complexity · Computer Science 2012-11-29 Bruno Escoffier , EunJung Kim , Vangelis Th. Paschos

This paper analyzes multi-step temporal difference (TD)-learning algorithms within the ``deadly triad'' scenario, characterized by linear function approximation, off-policy learning, and bootstrapping. In particular, we prove that $n$-step…

Machine Learning · Computer Science 2026-02-24 Han-Dong Lim , Donghwan Lee

We develop and analyze an asynchronous algorithm for distributed convex optimization when the objective writes a sum of smooth functions, local to each worker, and a non-smooth function. Unlike many existing methods, our distributed…

Optimization and Control · Mathematics 2019-12-13 Konstantin Mishchenko , Franck Iutzeler , Jérôme Malick

We consider off-policy temporal-difference (TD) learning methods for policy evaluation in Markov decision processes with finite spaces and discounted reward criteria, and we present a collection of convergence results for several…

Machine Learning · Computer Science 2018-03-30 Huizhen Yu

In this paper we discuss $\l$-policy iteration, a method for exact and approximate dynamic programming. It is intermediate between the classical value iteration (VI) and policy iteration (PI) methods, and it is closely related to optimistic…

Systems and Control · Computer Science 2015-07-07 Dimitri P. Bertsekas