66 citations · 283 across the 24 of their papers we have counts for
8 papers · 1 filter
Peppy: An AI-Assisted Workflow for Tight Convergence Analysis of Optimization Algorithms
Jaewook J. Suh, TaeHo Yoon, Edward Duc Hien Nguyen +2
This paper presents Peppy, an AI-assisted workflow for discovering tight, analytic convergence proofs for first-order optimization algorithms. Generic approaches to using LLMs to c…
Sparse factorization of the square all-ones matrix of arbitrary order
Xin Jiang, Edward Duc Hien Nguyen, César A. Uribe +1
In this paper, we study sparse factorization of the (scaled) square all-ones matrix of arbitrary order. We introduce the concept of hierarchically banded matrices and propose t…
On graphs with finite-time consensus and their use in gradient tracking
Edward Duc Hien Nguyen, Xin Jiang, Bicheng Ying +1
This paper studies sequences of graphs satisfying the finite-time consensus property (i.e., iterating through such a finite sequence is equivalent to performing global or exact ave…
Performance Limits of Stochastic Sub-Gradient Learning, Part II: Multi-Agent Case
Bicheng Ying, Ali H. Sayed
The analysis in Part I revealed interesting properties for subgradient learning algorithms in the context of stochastic optimization when gradient noise is present. These algorithm…
Exact Diffusion for Distributed Optimization and Learning --- Part II: Convergence Analysis
Kun Yuan, Bicheng Ying, Xiaochuan Zhao +1
Part I of this work [2] developed the exact diffusion algorithm to remove the bias that is characteristic of distributed solutions for deterministic optimization problems. The algo…
Exact Diffusion for Distributed Optimization and Learning --- Part I: Algorithm Development
Kun Yuan, Bicheng Ying, Xiaochuan Zhao +1
This work develops a distributed optimization strategy with guaranteed exact convergence for a broad class of left-stochastic combination policies. The resulting exact diffusion st…
On the Influence of Momentum Acceleration on Online Learning
Kun Yuan, Bicheng Ying, Ali H. Sayed
The article examines in some detail the convergence rate and mean-square-error performance of momentum stochastic gradient methods in the constant step-size and slow adaptation reg…
Online Dual Coordinate Ascent Learning
Bicheng Ying, Kun Yuan, Ali H. Sayed
The stochastic dual coordinate-ascent (S-DCA) technique is a useful alternative to the traditional stochastic gradient-descent algorithm for solving large-scale optimization proble…