English
Related papers

Related papers: Efficiently Escaping Saddle Points for Policy Opti…

200 papers

Policy optimization on high-dimensional continuous control tasks exhibits its difficulty caused by the large variance of the policy gradient estimators. We present the action subspace dependent gradient (ASDG) estimator which incorporates…

Machine Learning · Computer Science 2019-05-30 Jiajin Li , Baoxiang Wang

In this work, we conduct the first systematic study of stochastic variational inequality (SVI) and stochastic saddle point (SSP) problems under the constraint of differential privacy (DP). We propose two algorithms: Noisy Stochastic…

Optimization and Control · Mathematics 2022-04-04 Digvijay Boob , Cristóbal Guzmán

Variance reduction techniques are designed to decrease the sampling variance, thereby accelerating convergence rates of first-order (FO) and zeroth-order (ZO) optimization methods. However, in composite optimization problems, ZO methods…

Machine Learning · Computer Science 2024-05-29 Hao Di , Haishan Ye , Yueling Zhang , Xiangyu Chang , Guang Dai , Ivor W. Tsang

Heavy-tailed noise is pervasive in modern machine learning applications, arising from data heterogeneity, outliers, and non-stationary stochastic environments. While second-order methods can significantly accelerate convergence in…

Optimization and Control · Mathematics 2025-10-14 Abdurakhmon Sadiev , Peter Richtárik , Ilyas Fatkhullin

Reinforcement learning is essential for neural architecture search and hyperparameter optimization, but the conventional approaches impede widespread use due to prohibitive time and computational costs. Inspired by DeepSeek-V3 multi-token…

Machine Learning · Computer Science 2025-06-19 Zheng Li , Jerry Cheng , Huanying Helen Gu

In this paper, we propose a variant of Riemannian stochastic recursive gradient method that can achieve second-order convergence guarantee and escape saddle points using simple perturbation. The idea is to perturb the iterates when gradient…

Optimization and Control · Mathematics 2020-10-30 Andi Han , Junbin Gao

First order policy optimization has been widely used in reinforcement learning. It guarantees to find the optimal policy for the state-feedback linear quadratic regulator (LQR). However, the performance of policy optimization remains…

Optimization and Control · Mathematics 2022-04-05 Yang Zheng , Yue Sun , Maryam Fazel , Na Li

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

Machine learning problems such as neural network training, tensor decomposition, and matrix factorization, require local minimization of a nonconvex function. This local minimization is challenged by the presence of saddle points, of which…

Optimization and Control · Mathematics 2018-07-23 Santiago Paternain , Aryan Mokhtari , Alejandro Ribeiro

We consider distributed smooth nonconvex unconstrained optimization over networks, modeled as a connected graph. We examine the behavior of distributed gradient-based algorithms near strict saddle points. Specifically, we establish that (i)…

Optimization and Control · Mathematics 2020-05-26 Amir Daneshmand , Gesualdo Scutari , Vyacheslav Kungurtsev

We propose a second-order (Hessian or Hessian-free) based optimization method for variational inference inspired by Gaussian backpropagation, and argue that quasi-Newton optimization can be developed as well. This is accomplished by…

Machine Learning · Statistics 2017-03-30 Kai Fan , Ziteng Wang , Jeff Beck , James Kwok , Katherine Heller

This paper proposes low-complexity algorithms for finding approximate second-order stationary points (SOSPs) of problems with smooth non-convex objective and linear constraints. While finding (approximate) SOSPs is computationally…

Optimization and Control · Mathematics 2019-07-11 Songtao Lu , Meisam Razaviyayn , Bo Yang , Kejun Huang , Mingyi Hong

We address the discounted reward setting in reinforcement learning (RL). To mitigate the value approximation challenges in policy gradient methods, actor-critic approaches have been developed and are known to converge to stationary points…

Machine Learning · Computer Science 2026-05-15 Sanjeev Manivannan , Shuban V

This paper focuses on solving a stochastic saddle point problem (SPP) under an overparameterized regime for the case, when the gradient computation is impractical. As an intermediate step, we generalize Same-sample Stochastic Extra-gradient…

Optimization and Control · Mathematics 2024-06-05 Ekaterina Statkevich , Sofiya Bondar , Darina Dvinskikh , Alexander Gasnikov , Aleksandr Lobanov

Despite their popularity in the field of continuous optimisation, second-order quasi-Newton methods are challenging to apply in machine learning, as the Hessian matrix is intractably large. This computational burden is exacerbated by the…

Machine Learning · Computer Science 2024-02-28 Elre T. Oldewage , Ross M. Clarke , José Miguel Hernández-Lobato

We consider the case of derivative-free algorithms for non-convex optimization, also known as zero order algorithms, that use only function evaluations rather than gradients. For a wide variety of gradient approximators based on finite…

Optimization and Control · Mathematics 2019-10-30 Lampros Flokas , Emmanouil-Vasileios Vlatakis-Gkaragkounis , Georgios Piliouras

Rapid advances in data collection and processing capabilities have allowed for the use of increasingly complex models that give rise to nonconvex optimization problems. These formulations, however, can be arbitrarily difficult to solve in…

Multiagent Systems · Computer Science 2020-04-01 Stefan Vlaski , Ali H. Sayed

In this paper, we propose and analyze zeroth-order stochastic approximation algorithms for nonconvex and convex optimization, with a focus on addressing constrained optimization, high-dimensional setting and saddle-point avoiding. To handle…

Optimization and Control · Mathematics 2019-01-16 Krishnakumar Balasubramanian , Saeed Ghadimi

Stochastic proximal point methods have recently garnered renewed attention within the optimization community, primarily due to their desirable theoretical properties. Notably, these methods exhibit a convergence rate that is independent of…

Optimization and Control · Mathematics 2024-12-19 Elnur Gasanov , Peter Richtárik

This paper shows that a perturbed form of gradient descent converges to a second-order stationary point in a number iterations which depends only poly-logarithmically on dimension (i.e., it is almost "dimension-free"). The convergence rate…

Machine Learning · Computer Science 2017-03-03 Chi Jin , Rong Ge , Praneeth Netrapalli , Sham M. Kakade , Michael I. Jordan