no code implementations • 7 May 2024 • Zhifa Ke, Zaiwen Wen, Junyu Zhang
Temporal difference (TD) learning algorithms with neural network function parameterization have well-established empirical success in many practical large-scale reinforcement learning tasks.
1 code implementation • 3 Jul 2023 • Cheng Chen, Ruitao Chen, Tianyou Li, Ruichen Ao, Zaiwen Wen
Binary optimization has a wide range of applications in combinatorial optimization problems such as MaxCut, MIMO detection, and MaxSAT.
no code implementations • 19 Mar 2023 • Tianyou Li, Fan Chen, Huajie Chen, Zaiwen Wen
Understanding stochastic gradient descent (SGD) and its variants is essential for machine learning.
no code implementations • 25 Feb 2023 • Zhifa Ke, Junyu Zhang, Zaiwen Wen
Under mild conditions, non-asymptotic finite-sample convergence to the globally optimal Q function is derived for various nonlinear function approximations.
no code implementations • 15 Jul 2022 • Jiang Hu, Ruicheng Ao, Anthony Man-Cho So, MingHan Yang, Zaiwen Wen
Moreover, we show that if the loss function satisfies certain convexity and smoothness conditions and the input-output map satisfies a Riemannian Jacobian stability condition, then our proposed method enjoys a local linear -- or, under the Lipschitz continuity of the Riemannian Jacobian of the input-output map, even quadratic -- rate of convergence.
no code implementations • 13 Jul 2022 • Fan Chen, Junyu Zhang, Zaiwen Wen
As an important framework for safe Reinforcement Learning, the Constrained Markov Decision Process (CMDP) has been extensively studied in the recent literature.
1 code implementation • 14 Jun 2021 • MingHan Yang, Dong Xu, Qiwen Cui, Zaiwen Wen, Pengxiang Xu
In this paper, a novel second-order method called NG+ is proposed.
no code implementations • 20 May 2021 • Yongfeng Li, Mingming Zhao, WeiJie Chen, Zaiwen Wen
A general theoretical analysis shows that the solutions generated from a sequence of the constrained optimizations converge to the optimal solution of the LP if the error is controlled properly.
no code implementations • 10 Aug 2020 • Jinxin Wang, Fan Zhang, Zhonglin Xie, Gong Zhang, Zaiwen Wen
Almost all existing works deal with such a problem using relaxation techniques to transform it to be a convex optimization problem.
no code implementations • CVPR 2021 • Ming-Han Yang, Dong Xu, Hongyu Chen, Zaiwen Wen, Mengyun Chen
In this paper, we consider stochastic second-order methods for minimizing a finite summation of nonconvex functions.
1 code implementation • 10 Jun 2020 • Ming-Han Yang, Dong Xu, Zaiwen Wen, Mengyun Chen, Pengxiang Xu
Experiments on the distributed large-batch training show that the scaling efficiency is quite reasonable.
no code implementations • 21 Oct 2019 • Ming-Han Yang, Andre Milzarek, Zaiwen Wen, Tong Zhang
In this paper, a novel stochastic extra-step quasi-Newton method is developed to solve a class of nonsmooth nonconvex composite optimization problems.
no code implementations • 14 Oct 2018 • Yaqi Duan, Mengdi Wang, Zaiwen Wen, Yaxiang Yuan
The efficiency and statistical properties of our approach are illustrated on synthetic data.
1 code implementation • 3 Sep 2018 • Jiang Hu, Bo Jiang, Lin Lin, Zaiwen Wen, Yaxiang Yuan
In particular, we are interested in applications that the Euclidean Hessian itself consists of a computational cheap part and a significantly expensive part.
Optimization and Control
no code implementations • 9 Mar 2018 • Andre Milzarek, Xiantao Xiao, Shicong Cen, Zaiwen Wen, Michael Ulbrich
In this work, we present a globalized stochastic semismooth Newton method for solving stochastic optimization problems involving smooth nonconvex and nonsmooth convex terms in the objective function.
2 code implementations • 7 Aug 2017 • Jiang Hu, Andre Milzarek, Zaiwen Wen, Yaxiang Yuan
Optimization on Riemannian manifolds widely arises in eigenvalue computation, density functional theory, Bose-Einstein condensates, low rank nearest correlation, image registration, and signal processing, etc.
Optimization and Control
no code implementations • 29 Nov 2012 • Lanhui Wang, Amit Singer, Zaiwen Wen
An approximation to the least squares global self consistency error was obtained using convex relaxation by semidefinite programming.
no code implementations • 6 Mar 2011 • Yangyang Xu, Wotao Yin, Zaiwen Wen, Yin Zhang
By taking the advantages of both nonnegativity and low-rankness, one can generally obtain superior results than those of just using one of the two properties.
Information Theory Numerical Analysis Information Theory Numerical Analysis