English
Related papers

Related papers: A Variance-Reduced Cubic-Regularized Newton for Po…

200 papers

We consider the problem of control in the setting of reinforcement learning (RL), where model information is not available. Policy gradient algorithms are a popular solution approach for this problem and are usually shown to converge to a…

Machine Learning · Computer Science 2023-04-24 Mizhaan Prajit Maniyar , Akash Mondal , Prashanth L. A. , Shalabh Bhatnagar

We propose a stochastic variance-reduced cubic regularized Newton method for non-convex optimization. At the core of our algorithm is a novel semi-stochastic gradient along with a semi-stochastic Hessian, which are specifically designed for…

Machine Learning · Computer Science 2018-02-14 Dongruo Zhou , Pan Xu , Quanquan Gu

This paper addresses the optimization problem of minimizing non-convex continuous functions, which is relevant in the context of high-dimensional machine learning applications characterized by over-parametrization. We analyze a randomized…

Machine Learning · Computer Science 2025-02-28 Jim Zhao , Aurelien Lucchi , Nikita Doikov

Cubic regularization (CR) is an optimization method with emerging popularity due to its capability to escape saddle points and converge to second-order stationary solutions for nonconvex optimization. However, CR encounters a high sample…

Optimization and Control · Mathematics 2018-10-10 Zhe Wang , Yi Zhou , Yingbin Liang , Guanghui Lan

Reinforcement learning (RL) policies represented in Reproducing Kernel Hilbert Spaces (RKHS) offer powerful representational capabilities. While second-order optimization methods like Newton's method demonstrate faster convergence than…

Machine Learning · Computer Science 2025-06-03 Yixian Zhang , Huaze Tang , Chao Wang , Wenbo Ding

We consider the problem of risk-sensitive control in a reinforcement learning (RL) framework. In particular, we aim to find a risk-optimal policy by maximizing the distortion riskmetric (DRM) of the discounted reward in a finite horizon…

Machine Learning · Computer Science 2025-08-12 Soumen Pachal , Mizhaan Prajit Maniyar , Prashanth L. A

Second-order optimization methods, such as cubic regularized Newton methods, are known for their rapid convergence rates; nevertheless, they become impractical in high-dimensional problems due to their substantial memory requirements and…

Optimization and Control · Mathematics 2024-01-09 Ruichen Jiang , Parameswaran Raman , Shoham Sabach , Aryan Mokhtari , Mingyi Hong , Volkan Cevher

The cubic regularized Newton method of Nesterov and Polyak has become increasingly popular for non-convex optimization because of its capability of finding an approximate local solution with second-order guarantee. Several recent works…

Optimization and Control · Mathematics 2018-11-29 Junyu Zhang , Lin Xiao , Shuzhong Zhang

We propose a stochastic variance-reduced cubic regularized Newton algorithm to optimize the finite-sum problem over a Riemannian submanifold of the Euclidean space. The proposed algorithm requires a full gradient and Hessian update at the…

Optimization and Control · Mathematics 2022-12-14 Dewei Zhang , Sam Davanloo Tajbakhsh

In this paper, we propose several new stochastic second-order algorithms for policy optimization that only require gradient and Hessian-vector product in each iteration, making them computationally efficient and comparable to policy…

Optimization and Control · Mathematics 2023-01-31 Jinsong Liu , Chenghan Xie , Qi Deng , Dongdong Ge , Yinyu Ye

We study the performance of Stochastic Cubic Regularized Newton (SCRN) on a class of functions satisfying gradient dominance property with $1\le\alpha\le2$ which holds in a wide range of applications in machine learning and signal…

Machine Learning · Computer Science 2023-01-24 Saeed Masiha , Saber Salehkaleybar , Niao He , Negar Kiyavash , Patrick Thiran

We study the sample complexity of reducing reinforcement learning to a sequence of empirical risk minimization problems over the policy space. Such reductions-based algorithms exhibit local convergence in the function space, as opposed to…

Machine Learning · Computer Science 2023-01-26 Naman Agarwal , Brian Bullins , Karan Singh

Stochastic variance reduction has proven effective at accelerating first-order algorithms for solving convex finite-sum optimization tasks such as empirical risk minimization. Incorporating second-order information has proven helpful in…

Optimization and Control · Mathematics 2025-04-30 Michał Dereziński

Policy gradient (PG) is widely used in reinforcement learning due to its scalability and good performance. In recent years, several variance-reduced PG methods have been proposed with a theoretical guarantee of converging to an approximate…

Machine Learning · Computer Science 2025-10-01 Sadegh Khorasani , Saber Salehkaleybar , Negar Kiyavash , Niao He , Matthias Grossglauser

In this paper, we consider an unconstrained optimization model where the objective is a sum of a large number of possibly nonconvex functions, though overall the objective is assumed to be smooth and convex. Our bid to solving such model…

Optimization and Control · Mathematics 2022-03-15 Xi Chen , Bo Jiang , Tianyi Lin , Shuzhong Zhang

In this paper, we propose a new randomized second-order optimization algorithm---Stochastic Subspace Cubic Newton (SSCN)---for minimizing a high dimensional convex function $f$. Our method can be seen both as a {\em stochastic} extension of…

Optimization and Control · Mathematics 2020-02-25 Filip Hanzely , Nikita Doikov , Peter Richtárik , Yurii Nesterov

A class of second-order algorithms is proposed for minimizing smooth nonconvex functions that alternates between regularized Newton and negative curvature steps in an iteration-dependent subspace. In most cases, the Hessian matrix is…

Optimization and Control · Mathematics 2023-08-22 Serge Gratton , Sadok Jerad , Philippe L. Toint

We present two new remarkably simple stochastic second-order methods for minimizing the average of a very large number of sufficiently smooth and strongly convex functions. The first is a stochastic variant of Newton's method (SN), and the…

Machine Learning · Computer Science 2019-12-04 Dmitry Kovalev , Konstantin Mishchenko , Peter Richtárik

Policy gradient methods are a powerful family of reinforcement learning algorithms for continuous control that optimize a policy directly. However, standard first-order methods often converge slowly. Second-order methods can accelerate…

Systems and Control · Electrical Eng. & Systems 2025-11-05 Amirreza Valaei , Arash Bahari Kordabad , Sadegh Soudjani

The cubic regularization (CR) algorithm has attracted a lot of attentions in the literature in recent years. We propose a new reformulation of the cubic regularization subproblem. The reformulation is an unconstrained convex problem that…

Optimization and Control · Mathematics 2021-12-20 Rujun Jiang , Zhishuo Zhou , Zirui Zhou
‹ Prev 1 2 3 10 Next ›