From the 2 of 11 linked papers with an AI index.
11 papers
Halpern Iteration Achieves th-Order Oracle Complexity for Monotone Variational Inequalities
Lesi Chen, Xinliang Zhang, Hengyu Wang +3
We study second- and higher-order methods for solving smooth monotone variational inequalities (MVI). Monteiro and Svaiter (SIAM J. Optim., 2012) showed that a second-order method,…
Quantum Speedups for Stochastic Optimization with Heavy-Tailed Noise
Bin Luo, Chengchang Liu, Jonathan Allcock +2
The paper proposes quantum mean estimators for heavy‑tailed random variables and uses them to design quantum stochastic gradient descent methods that achieve lower query complexity…
Optimal Convex Optimization with Inexact Second-Order Oracles
Lesi Chen, Chengchang Liu, Luo Luo +2
In this paper, we present a novel second-order method called Accelerated Inexact Newton Extragradient (AINE) for convex optimization using -inexact Hessians. We show that AINE…
On the Convergence of Stochastic Low-Rank Adaptation
Ru Wang, Chengchang Liu, John C. S. Lui
Low-rank adaptation (LoRA) optimizes over two adapters and that form a low-…
Faster Newton Methods for Convex and Nonconvex Optimization in Gradient Complexity
Lesi Chen, Chengchang Liu, Luo Luo +1
The paper proposes new second‑order optimization algorithms that reduce the gradient complexity for both convex and nonconvex problems, establishing tighter theoretical bounds than…
Universal Tensor Methods for Monotone Variational Inequalities
Chengchang Liu, John C. S. Lui, Luo Luo
We study monotone variational inequalities whose operators have Hölder continuous higher-order derivatives. For a fixed order , we assume that the -th derivative o…