English
Related papers

Related papers: Provably Efficient Convergence of Primal-Dual Acto…

200 papers

We consider an improper reinforcement learning setting where a learner is given $M$ base controllers for an unknown Markov decision process, and wishes to combine them optimally to produce a potentially new controller that can outperform…

Machine Learning · Computer Science 2022-07-20 Mohammadi Zaki , Avinash Mohan , Aditya Gopalan , Shie Mannor

In this work, we establish the linear convergence estimate for the gradient descent involving the delay $\tau\in\mathbb{N}$ when the cost function is $\mu$-strongly convex and $L$-smooth. This result improves upon the well-known estimates…

Optimization and Control · Mathematics 2024-02-23 Hyung Jun Choi , Woocheol Choi , Jinmyoung Seok

We consider the problem of finding the minimizations of the sum of two convex functions and the composition of another convex function with a continuous linear operator from the view of fixed point algorithms based on proximity operators,…

Optimization and Control · Mathematics 2016-04-18 Meng Wen , Yu-Chao Tang , Jigen Peng

This paper introduces a coordinate descent version of the V\~u-Condat algorithm. By coordinate descent, we mean that only a subset of the coordinates of the primal and dual iterates is updated at each iteration, the other coordinates being…

Optimization and Control · Mathematics 2019-01-17 Olivier Fercoq , Pascal Bianchi

In this paper, we propose a continuous-time primal-dual approach for linearly constrained multiobjective optimization problems. A novel dynamical model, called accelerated multiobjective primal-dual flow, is presented with a second-order…

Optimization and Control · Mathematics 2025-11-06 Hao Luo , Qiaoyuan Shu , Xinmin Yang

This work presents a universal accelerated first-order primal-dual method for affinely constrained convex optimization problems. It can handle both Lipschitz and H\"{o}lder gradients but does not need to know the smoothness level of the…

Optimization and Control · Mathematics 2022-11-09 Hao Luo

We study policy gradient (PG) for reinforcement learning in continuous time and space under the regularized exploratory formulation developed by Wang et al. (2020). We represent the gradient of the value function with respect to a given…

Machine Learning · Computer Science 2022-07-26 Yanwei Jia , Xun Yu Zhou

This paper studies the continuous-time dynamics of primal-dual algorithms for linearly constrained convex optimization problems and provides a quantitative convergence analysis using the Lyapunov functions. With the growing prevalence of…

Optimization and Control · Mathematics 2026-05-26 Chise Ishii , Yasushi Narushima

In this paper, we adapt proximal incremental aggregated gradient methods to saddle point problems, which is motivated by decoupling linear transformations in regularized empirical risk minimization models. First, the Primal-Dual Proximal…

Optimization and Control · Mathematics 2019-11-14 Zhou Xianchen , Peng Wei , Wang Hongxia

As an important algorithm in deep reinforcement learning, advantage actor critic (A2C) has been widely succeeded in both discrete and continuous control tasks with raw pixel inputs, but its sample efficiency still needs to improve more. In…

Machine Learning · Computer Science 2022-02-15 Yuan Wang , Chunyuan Zhang , Tianzong Yu , Meng Ma

Bilevel optimization has been developed for many machine learning tasks with large-scale and high-dimensional data. This paper considers a constrained bilevel optimization problem, where the lower-level optimization problem is convex with…

Machine Learning · Computer Science 2023-08-22 Siyuan Xu , Minghui Zhu

Despite its popularity in the reinforcement learning community, a provably convergent policy gradient method for continuous space-time control problems with nonlinear state dynamics has been elusive. This paper proposes proximal gradient…

Optimization and Control · Mathematics 2022-12-27 Christoph Reisinger , Wolfgang Stockinger , Yufei Zhang

In this paper, we consider optimizing a smooth, convex, lower semicontinuous function in Riemannian space with constraints. To solve the problem, we first convert it to a dual problem and then propose a general primal-dual algorithm to…

Machine Learning · Computer Science 2020-05-20 Shijun Wang , Baocheng Zhu , Lintao Ma , Yuan Qi

We develop a second order primal-dual method for optimization problems in which the objective function is given by the sum of a strongly convex twice differentiable term and a possibly nondifferentiable convex regularizer. After introducing…

Optimization and Control · Mathematics 2020-08-31 Neil K. Dhingra , Sei Zhen Khong , Mihailo R. Jovanović

This note is concerned with the problem of minimizing a separable, convex, composite (smooth and nonsmooth) function subject to linear constraints. We study a randomized block-coordinate interpretation of the Chambolle-Pock primal-dual…

Optimization and Control · Mathematics 2024-08-30 Olivier Bilenne

Gradient algorithms are classical in adaptive control and parameter estimation. For instantaneous quadratic cost functions they lead to a linear time-varying dynamic system that converges exponentially under persistence of excitation…

Optimization and Control · Mathematics 2020-10-06 Juan G. Rueda-Escobedo , Jaime A. Moreno

Motivated by broad applications in machine learning, we study the popular accelerated stochastic gradient descent (ASGD) algorithm for solving (possibly nonconvex) optimization problems. We characterize the finite-time performance of this…

Optimization and Control · Mathematics 2020-10-20 Thinh T. Doan , Lam M. Nguyen , Nhan H. Pham , Justin Romberg

Markov Decision Processes are classically solved using Value Iteration and Policy Iteration algorithms. Recent interest in Reinforcement Learning has motivated the study of methods inspired by optimization, such as gradient ascent. Among…

Machine Learning · Computer Science 2021-05-05 Sajad Khodadadian , Prakirt Raj Jhunjhunwala , Sushil Mahavir Varma , Siva Theja Maguluri

This work examines average-reward reinforcement learning with general policy parametrization. Existing state-of-the-art (SOTA) guarantees for this problem are either suboptimal or hindered by several challenges, including poor scalability…

Machine Learning · Computer Science 2025-05-07 Swetha Ganesh , Washim Uddin Mondal , Vaneet Aggarwal

Reinforcement learning (RL) is a fundamental framework for sequential decision-making, in which an agent learns an optimal policy through interactions with an unknown environment. In settings with function approximation, many existing RL…

Machine Learning · Computer Science 2026-05-05 Ruiquan Huang , Donghao Li , Yingbin Liang , Jing Yang