English
Related papers

Related papers: Efficiently Escaping Saddle Points for Policy Opti…

200 papers

Local search heuristics for non-convex optimizations are popular in applied machine learning. However, in general it is hard to guarantee that such algorithms even converge to a local minimum, due to the existence of complicated saddle…

Machine Learning · Computer Science 2016-02-19 Anima Anandkumar , Rong Ge

A central challenge to using first-order methods for optimizing nonconvex problems is the presence of saddle points. First-order methods often get stuck at saddle points, greatly deteriorating their performance. Typically, to escape from…

Machine Learning · Computer Science 2017-09-06 Sashank J Reddi , Manzil Zaheer , Suvrit Sra , Barnabas Poczos , Francis Bach , Ruslan Salakhutdinov , Alexander J Smola

Natural policy gradient (NPG) and its variants are widely-used policy search methods in reinforcement learning. Inspired by prior work, a new NPG variant coined NPG-HM is developed in this paper, which utilizes the Hessian-aided momentum…

Machine Learning · Computer Science 2024-01-23 Jie Feng , Ke Wei , Jinchi Chen

Policy gradient (PG) methods are a class of effective reinforcement learning algorithms, particularly when dealing with continuous control problems. They rely on fresh on-policy data, making them sample-inefficient and requiring…

Machine Learning · Computer Science 2026-02-03 Alessandro Montenegro , Federico Mansutti , Marco Mussi , Matteo Papini , Alberto Maria Metelli

In recent centralized nonconvex distributed learning and federated learning, local methods are one of the promising approaches to reduce communication time. However, existing work has mainly focused on studying first-order optimality…

Machine Learning · Computer Science 2022-10-13 Tomoya Murata , Taiji Suzuki

Policy gradient methods are powerful reinforcement learning algorithms and have been demonstrated to solve many complex tasks. However, these methods are also data-inefficient, afflicted with high variance gradient estimates, and frequently…

Machine Learning · Computer Science 2019-05-15 Andreas Doerr , Michael Volpp , Marc Toussaint , Sebastian Trimpe , Christian Daniel

Gradient descent and its variants are widely used in machine learning. However, oracle access of gradient may not be available in many applications, limiting the direct use of gradient descent. This paper proposes a method of estimating…

Optimization and Control · Mathematics 2019-10-07 Qinbo Bai , Mridul Agarwal , Vaneet Aggarwal

Two-point zeroth order methods are important in many applications of zeroth-order optimization, such as robotics, wind farms, power systems, online optimization, and adversarial robustness to black-box attacks in deep neural networks, where…

Optimization and Control · Mathematics 2023-05-10 Zhaolin Ren , Yujie Tang , Na Li

Variance reduction techniques like SVRG provide simple and fast algorithms for optimizing a convex finite-sum objective. For nonconvex objectives, these techniques can also find a first-order stationary point (with small gradient). However,…

Machine Learning · Computer Science 2019-05-03 Rong Ge , Zhize Li , Weiyao Wang , Xiang Wang

We show that on-policy policy gradient (PG) and its variance reduction variants can be derived by taking finite difference of function evaluations supplied by estimators from the importance sampling (IS) family for off-policy evaluation…

Machine Learning · Computer Science 2020-06-25 Jiawei Huang , Nan Jiang

A central challenge to many fields of science and engineering involves minimizing non-convex error functions over continuous, high dimensional spaces. Gradient descent or quasi-Newton methods are almost ubiquitously used to perform such…

Machine Learning · Computer Science 2014-06-11 Yann Dauphin , Razvan Pascanu , Caglar Gulcehre , Kyunghyun Cho , Surya Ganguli , Yoshua Bengio

Pruning neural networks reduces inference time and memory costs. On standard hardware, these benefits will be especially prominent if coarse-grained structures, like feature maps, are pruned. We devise two novel saliency-based methods for…

Machine Learning · Computer Science 2023-09-26 Manuel Nonnenmacher , Thomas Pfeil , Ingo Steinwart , David Reeb

Improving sample efficiency has been a longstanding goal in reinforcement learning. This paper proposes $\mathtt{VRMPO}$ algorithm: a sample efficient policy gradient method with stochastic mirror descent. In $\mathtt{VRMPO}$, a novel…

Machine Learning · Computer Science 2022-02-10 Long Yang , Yu Zhang , Gang Zheng , Qian Zheng , Pengfei Li , Jianhang Huang , Jun Wen , Gang Pan

In this paper, we study stochastic non-convex optimization with non-convex random functions. Recent studies on non-convex optimization revolve around establishing second-order convergence, i.e., converging to a nearly second-order optimal…

Optimization and Control · Mathematics 2017-11-02 Mingrui Liu , Tianbao Yang

We analyze stochastic gradient algorithms for optimizing nonconvex problems. In particular, our goal is to find local minima (second-order stationary points) instead of just finding first-order stationary points which may be some bad…

Machine Learning · Computer Science 2019-06-24 Zhize Li

Gradient dominance property is a condition weaker than strong convexity, yet sufficiently ensures global convergence even in non-convex optimization. This property finds wide applications in machine learning, reinforcement learning (RL),…

Optimization and Control · Mathematics 2024-05-30 Jiyuan Tan , Chenyu Xue , Chuwen Zhang , Qi Deng , Dongdong Ge , Yinyu Ye

We consider escaping saddle points of nonconvex problems where only the function evaluations can be accessed. Although a variety of works have been proposed, the majority of them require either second or first-order information, and only a…

Optimization and Control · Mathematics 2022-10-05 Hualin Zhang , Huan Xiong , Bin Gu

Backtracking search algorithms are often used to solve the Constraint Satisfaction Problem (CSP). The efficiency of backtracking search depends greatly on the variable ordering heuristics. Currently, the most commonly used heuristics are…

Artificial Intelligence · Computer Science 2021-12-28 Wen Song , Zhiguang Cao , Jie Zhang , Andrew Lim

We consider stochastic unconstrained bilevel optimization problems when only the first-order gradient oracles are available. While numerous optimization methods have been proposed for tackling bilevel problems, existing methods either tend…

Optimization and Control · Mathematics 2023-01-27 Jeongyeol Kwon , Dohyun Kwon , Stephen Wright , Robert Nowak

As the most successful variant and improvement for Trust Region Policy Optimization (TRPO), proximal policy optimization (PPO) has been widely applied across various domains with several advantages: efficient data utilization, easy…

Machine Learning · Computer Science 2019-02-15 Xiangxiang Chu