English
Related papers

Related papers: Convergence of Policy Mirror Descent Beyond Compat…

200 papers

A wide range of applications arising in machine learning and signal processing can be cast as convex optimization problems. These problems are often ill-posed, i.e., the optimal solution lacks a desired property such as uniqueness or…

Optimization and Control · Mathematics 2019-07-18 Mostafa Amini , Farzad Yousefian

Theoretical estimates of the convergence rate of many well-known gradient-type optimization methods are based on quadratic interpolation, provided that the Lipschitz condition for the gradient is satisfied. In this article we obtain a…

Optimization and Control · Mathematics 2018-12-18 Fedor S. Stonyakin

We investigate Stochastic Mirror Descent (SMD) with matrix parameters and vector-valued predictions, a framework relevant to multi-class classification and matrix completion problems. Focusing on the overparameterized regime, where the…

Machine Learning · Statistics 2026-03-02 Danil Akhtiamov , Reza Ghane , Omead Pooladzandi , Babak Hassibi

We propose and study a general framework for regularized Markov decision processes (MDPs) where the goal is to find an optimal policy that maximizes the expected discounted total reward plus a policy regularization term. The extant…

Machine Learning · Statistics 2019-10-22 Xiang Li , Wenhao Yang , Zhihua Zhang

First-order optimization methods tend to inherently favor certain solutions over others when minimizing an underdetermined training objective that has multiple global optima. This phenomenon, known as implicit bias, plays a critical role in…

Machine Learning · Computer Science 2024-04-09 Guanghui Wang , Zihao Hu , Claudio Gentile , Vidya Muthukumar , Jacob Abernethy

Masked diffusion models (MDMs) have recently emerged as a novel framework for language modeling. MDMs generate sentences by iteratively denoising masked sequences, filling in [MASK] tokens step by step. Although MDMs support any-order…

Machine Learning · Computer Science 2026-02-27 Chunsan Hong , Seonho An , Min-Soo Kim , Jong Chul Ye

This paper is devoted to a new modification of a recently proposed adaptive stochastic mirror descent algorithm for constrained convex optimization problems in the case of several convex functional constraints. Algorithms, standard and its…

Optimization and Control · Mathematics 2020-01-22 Mohammad S. Alkousa

The convergence of deterministic policy gradient under the Hadamard parameterization is studied in the tabular setting and the linear convergence of the algorithm is established. To this end, we first show that the error decreases at an…

Optimization and Control · Mathematics 2023-11-28 Jiacai Liu , Jinchi Chen , Ke Wei

Matrix completion has attracted much interest in the past decade in machine learning and computer vision. For low-rank promotion in matrix completion, the nuclear norm penalty is convenient due to its convexity but has a bias problem.…

Machine Learning · Computer Science 2019-03-05 Fei Wen , Rendong Ying , Peilin Liu , Trieu-Kien Truong

Learning-to-optimize is an emerging framework that leverages training data to speed up the solution of certain optimization problems. One such approach is based on the classical mirror descent algorithm, where the mirror map is modelled…

Optimization and Control · Mathematics 2023-06-05 Hong Ye Tan , Subhadip Mukherjee , Junqi Tang , Andreas Hauptmann , Carola-Bibiane Schönlieb

This paper is concerned with multi-agent optimization problem. A distributed randomized gradient-free mirror descent (DRGFMD) method is developed by introducing a randomized gradient-free oracle in the mirror descent scheme where the…

Optimization and Control · Mathematics 2019-03-12 Zhan Yu , Daniel W. C. Ho , Deming Yuan

Constrained decision-making is essential for designing safe policies in real-world control systems, yet simulated environments often fail to capture real-world adversities. We consider the problem of learning a policy that will maximize the…

Machine Learning · Computer Science 2026-02-10 Sourav Ganguly , Kishan Panaganti , Arnob Ghosh , Adam Wierman

We consider the problem of minimizing the sum of an average function of a large number of smooth convex components and a general, possibly non-differentiable, convex function. Although many methods have been proposed to solve this problem…

Optimization and Control · Mathematics 2019-01-01 Le Thi Khanh Hien , Cuong V. Nguyen , Huan Xu , Canyi Lu , Jiashi Feng

We propose a conditional gradient framework for a composite convex minimization template with broad applications. Our approach combines smoothing and homotopy techniques under the CGM framework, and provably achieves the optimal…

Optimization and Control · Mathematics 2018-08-21 Alp Yurtsever , Olivier Fercoq , Francesco Locatello , Volkan Cevher

In this work, we investigate the idea of variance reduction by studying its properties with general adaptive mirror descent algorithms in nonsmooth nonconvex finite-sum optimization problems. We propose a simple yet generalized framework…

Machine Learning · Statistics 2022-10-18 Wenjie Li , Zhanyu Wang , Yichen Zhang , Guang Cheng

Standard value function approaches to finding policies for Partially Observable Markov Decision Processes (POMDPs) are generally considered to be intractable for large models. The intractability of these algorithms is to a large extent a…

Artificial Intelligence · Computer Science 2011-10-05 N. Roy , G. Gordon , S. Thrun

We make three contributions toward better understanding policy gradient methods in the tabular setting. First, we show that with the true gradient, policy gradient with a softmax parametrization converges at a $O(1/t)$ rate, with constants…

Machine Learning · Computer Science 2022-06-03 Jincheng Mei , Chenjun Xiao , Csaba Szepesvari , Dale Schuurmans

Dual-based proportional-integral-derivative (PID) controllers are often employed in practice to solve online allocation problems with global constraints, such as budget pacing in online advertising. However, controllers are used in a…

Optimization and Control · Mathematics 2023-12-21 Santiago R. Balseiro , Haihao Lu , Vahab Mirrokni , Balasubramanian Sivan

In this paper we address the convergence of stochastic approximation when the functions to be minimized are not convex and nonsmooth. We show that the "mean-limit" approach to the convergence which leads, for smooth problems, to the ODE…

Optimization and Control · Mathematics 2018-05-08 Szymon Majewski , Błażej Miasojedow , Eric Moulines

We propose a new family of subgradient- and gradient-based methods which converges with optimal complexity for convex optimization problems whose feasible region is simple enough. This includes cases where the objective function is…

Optimization and Control · Mathematics 2016-08-19 Masaru Ito , Mituhiro Fukuda