4 papers · 1 filter
Halpern-Accelerated Majorized ADMM with Optimal Non-Ergodic Convergence under Degenerate Preconditioning
Ning Zhang, Benqi Liu, Liwei Zhang
We develop a Halpern-accelerated majorized alternating direction method of multipliers (ADMM) with possibly indefinite proximal terms for linearly constrained convex composite opti…
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…
A Quadratic-Approximation-Based Stochastic Approximation Method for Weakly Convex Stochastic Programming
Yule Zhang, Benqi Liu, Xiantao Xiao +1
We propose a novel stochastic approximation algorithm, termed PMQSopt, for solving weakly convex stochastic optimization problems involving expectation-valued functions. The algori…
A Proximal Augmented Lagrangian Method Based on Quadratic Approximations for Weakly Convex Optimization
Yule Zhang, Benqi Liu, Xiantao Xiao +1
This paper proposes QPALM, a proximal augmented Lagrangian method based on quadratic approximations, for solving nonlinear programming problems with weakly convex objective and con…