From the 1 of 6 linked papers with an AI index.
6 papers
HNAG: An Accelerated Gradient Method with a Refined Asymptotic Rate for Strongly Convex Optimization
Long Chen, Zeyi Xu
The paper introduces two accelerated first‑order algorithms, HNAG⁺ and HNAG⁺⁺, for smooth strongly convex problems, achieving optimal global convergence and a refined asymptotic ra…
Adaptive Accelerated Mirror Descent in Primal and Dual Spaces
Zeyi Xu, Long Chen
We propose Adaptive Accelerated Mirror Descent (AAMD), a flow-based method that combines nonlinear preconditioning, acceleration, and adaptivity in mirror geometry. The key ingredi…
Accelerating Sinkhorn for Entropy-Regularized Optimal Transport
Zeyi Xu, Long Chen
We propose Acc-Sinkhorn, a simple accelerated variant of Sinkhorn for entropy-regularized optimal transport (EOT). The method is derived from a bilevel optimization view: Sinkhorn…
Deterministic Adam-Inspired Methods with Accelerated Convergence Rate
Yaxin Yu, Long Chen, Zeyi Xu
Adam is widely used, but its convergence theory remains incomplete even in the deterministic full-batch setting because momentum and adaptive preconditioning are tightly coupled. F…
Adaptive Accelerated Gradient Descent Methods for Convex Optimization
Zeyi Xu, Long Chen
This work proposes AGD, a novel adaptive accelerated gradient descent method for convex and composite optimization. Smoothness and convexity constants are updated via Lyapunov…
Accelerated Mirror Descent Method through Variable and Operator Splitting
Long Chen, Hao Luo, Jingrong Wei +2
Mirror descent uses the mirror function to encode geometry and constraints, improving convergence while preserving feasibility. Accelerated Mirror Descent Methods (Acc-MD) are deri…