activity
20172026
most citedA Stochastic Extra-Step Quasi-Newton Method for Nonsmooth Nonconvex Optimization

6 citations · 22 across the 15 of their papers we have counts for

collaborators
Showing math.OCShow all

22 papers · 1 filter

math.OC2026

A counterexample to global convergence of classical DFP under the standard strong Wolfe conditions

Benqi Liu, Zichen Wang, Zaiwen Wen +2

A long-standing open question in quasi-Newton optimization asks whether the classical Davidon--Fletcher--Powell (DFP) method converges globally on uniformly convex objectives when…

math.OC2023

On the Optimal Lower and Upper Complexity Bounds for a Class of Composite Optimization Problems

Zhenyuan Zhu, Fan Chen, Junyu Zhang +1

We study the optimal lower and upper complexity bounds for finding approximate solutions to the composite problem , where is smooth and is convex. Giv…

math.OC2023

Monte Carlo Policy Gradient Method for Binary Optimization

Cheng Chen, Ruitao Chen, Tianyou Li +2

Binary optimization has a wide range of applications in combinatorial optimization problems such as MaxCut, MIMO detection, and MaxSAT. However, these problems are typically NP-har…

math.OC2023

The Error in Multivariate Linear Extrapolation with Applications to Derivative-Free Optimization

Liyuan Cao, Zaiwen Wen, Ya-xiang Yuan

We study in this paper the function approximation error of multivariate linear extrapolation. The sharp error bound of linear interpolation already exists in the literature. Howeve…

math.OC20211 cited

NG+ : A Multi-Step Matrix-Product Natural Gradient Method for Deep Learning

Minghan Yang, Dong Xu, Qiwen Cui +2

In this paper, a novel second-order method called NG+ is proposed. By following the rule ``the shape of the gradient equals the shape of the parameter", we define a generalized fis…

math.OC2021

A Stochastic Composite Augmented Lagrangian Method For Reinforcement Learning

Yongfeng Li, Mingming Zhao, Weijie Chen +1

In this paper, we consider the linear programming (LP) formulation for deep reinforcement learning. The number of the constraints depends on the size of state and action spaces, wh…