English
Related papers

Related papers: SBEED: Convergent Reinforcement Learning with Nonl…

200 papers

A Support Vector Method for multivariate performance measures was recently introduced by Joachims (2005). The underlying optimization problem is currently solved using cutting plane methods such as SVM-Perf and BMRM. One can show that these…

Machine Learning · Computer Science 2012-02-20 Xinhua Zhang , Ankan Saha , S. V. N. Vishwanatan

In the reinforcement learning literature, strong theoretical guarantees have been obtained for algorithms applicable to LTI systems. However, in the nonlinear case only weaker results have been obtained for algorithms that mostly rely on…

Systems and Control · Electrical Eng. & Systems 2026-04-01 Victor G. Lopez , Malte Heinrich , Matthias A. Müller

We develop an inexact primal-dual first-order smoothing framework to solve a class of non-bilinear saddle point problems with primal strong convexity. Compared with existing methods, our framework yields a significant improvement over the…

Optimization and Control · Mathematics 2023-07-25 Le Thi Khanh Hien , Renbo Zhao , William B. Haskell

We address the problem of learning an unknown smooth function and its derivatives from noisy pointwise evaluations under the supremum norm. While classical nonparametric regression provides a strong theoretical foundation, traditional…

Machine Learning · Computer Science 2026-03-10 Davide Maran , Marcello Restelli

The goal of the paper is development of an optimization method with the superlinear convergence rate for a nonsmooth convex function. For optimization an approximation is used that is similar to the Steklov integral averaging. The…

Optimization and Control · Mathematics 2023-08-03 I. M. Prudnikov

We study the problem of sampling from a target distribution in $\mathbb{R}^d$ whose potential is not smooth. Compared with the sampling problem with smooth potentials, this problem is much less well-understood due to the lack of smoothness.…

Computation · Statistics 2023-07-25 Jiaojiao Fan , Bo Yuan , Jiaming Liang , Yongxin Chen

The Bellman equation and its continuous form, the Hamilton-Jacobi-Bellman equation, are ubiquitous in reinforcement learning and control theory. However, these equations become intractable for high-dimensional or nonlinear systems. This…

Artificial Intelligence · Computer Science 2026-05-04 Preston Rozwood , Edward Mehrez , Ludger Paehler , Wen Sun , Steven L. Brunton

We study the performance of stochastic first-order methods for finding saddle points of convex-concave functions. A notorious challenge faced by such methods is that the gradients can grow arbitrarily large during optimization, which may…

Machine Learning · Computer Science 2024-06-10 Gergely Neu , Nneka Okolo

This paper focuses on the problem of minimizing a locally Lipschitz continuous function. Motivated by the effectiveness of Bregman gradient methods in training nonsmooth deep neural networks and the recent progress in stochastic subgradient…

Optimization and Control · Mathematics 2025-06-02 Kuangyu Ding , Kim-Chuan Toh

TD($\lambda$) with function approximation has proved empirically successful for some complex reinforcement learning problems. For linear approximation, TD($\lambda$) has been shown to minimise the squared error between the approximate value…

Machine Learning · Computer Science 2025-12-24 Lex Weaver , Jonathan Baxter

For a linear equality constrained convex optimization problem involving two objective functions with a ``nonsmooth" + ``nonsmooth" composite structure, we study two algorithms derived from a mixed-order dynamical system which incorporates…

Optimization and Control · Mathematics 2026-03-25 Geng-Hua Li , Hai-Yi Zhao , Xiangkai Sun

The proximal bundle method (PBM) is a fundamental and computationally effective algorithm for solving nonsmooth optimization problems. In this paper, we present the first variant of the PBM for smooth objectives, achieving an accelerated…

Optimization and Control · Mathematics 2025-04-30 David Fersztand , Xu Andy Sun

We propose a primal-dual smoothing framework for finding a near-stationary point of a class of non-smooth non-convex optimization problems with max-structure. We analyze the primal and dual gradient complexities of the framework via two…

Optimization and Control · Mathematics 2023-07-19 Renbo Zhao

Reinforcement learning (RL) problems are fundamental in online decision-making and have been instrumental in finding an optimal policy for Markov decision processes (MDPs). Function approximations are usually deployed to handle large or…

Machine Learning · Computer Science 2025-05-20 Jiashuo Jiang , Yiming Zong , Yinyu Ye

We consider a class of distributed optimization problem where the objective function consists of a sum of strongly convex and smooth functions and a (possibly nonsmooth) convex regularizer. A multi-agent network is assumed, where each agent…

Optimization and Control · Mathematics 2021-10-01 Yichuan Li , Yonghai Gong , Nikolaos M. Freris , Petros Voulgaris , Dusan Stipanovic

We address the optimization problem in a data-driven variational reconstruction framework, where the regularizer is parameterized by an input-convex neural network (ICNN). While gradient-based methods are commonly used to solve such…

Optimization and Control · Mathematics 2025-10-24 Matthias J. Ehrhardt , Subhadip Mukherjee , Hok Shing Wong

We study the optimization of non-convex functions that are not necessarily smooth (gradient and/or Hessian are Lipschitz) using first order methods. Smoothness is a restrictive assumption in machine learning in both theory and practice,…

Optimization and Control · Mathematics 2025-06-27 Daniel Yiming Cao , August Y. Chen , Karthik Sridharan , Benjamin Tang

In this paper, we propose an inertial accelerated primal-dual method for the linear equality constrained convex optimization problem. When the objective function has a ``nonsmooth + smooth'' composite structure, we further propose an…

Optimization and Control · Mathematics 2021-06-30 Xin He , Rong Hu , Ya-Ping Fang

We study the non-smooth optimization problems in machine learning, where both the loss function and the regularizer are non-smooth functions. Previous studies on efficient empirical loss minimization assume either a smooth loss function or…

Machine Learning · Computer Science 2013-07-29 Tianbao Yang , Mehrdad Mahdavi , Rong Jin , Shenghuo Zhu

Evolutionary strategies have recently been shown to achieve competing levels of performance for complex optimization problems in reinforcement learning. In such problems, one often needs to optimize an objective function subject to a set of…

Neural and Evolutionary Computing · Computer Science 2022-02-23 Youssef Diouane , Aurelien Lucchi , Vihang Patil
‹ Prev 1 4 5 6 7 8 10 Next ›