490 citations · 1.5k across the 111 of their papers we have counts for
6 papers · 1 filter
Symmetry, Saddle Points, and Global Optimization Landscape of Nonconvex Matrix Factorization
Xingguo Li, Junwei Lu, Raman Arora +4
We propose a general theory for studying the \xl{landscape} of nonconvex \xl{optimization} with underlying symmetric structures \tz{for a class of machine learning problems (e.g.,…
The Physical Systems Behind Optimization Algorithms
Lin F. Yang, R. Arora, V. Braverman +1
We use differential equations based approaches to provide some {\it \textbf{physics}} insights into analyzing the dynamics of popular optimization algorithms in machine learning. I…
On Faster Convergence of Cyclic Block Coordinate Descent-type Methods for Strongly Convex Minimization
Xingguo Li, Tuo Zhao, Raman Arora +2
The cyclic block coordinate descent-type (CBCD-type) methods, which performs iterative updates for a few coordinates (a block) simultaneously throughout the procedure, have shown r…
On Fast Convergence of Proximal Algorithms for SQRT-Lasso Optimization: Don't Worry About Its Nonsmooth Loss Function
Xingguo Li, Haoming Jiang, Jarvis Haupt +4
Many machine learning techniques sacrifice convenient computational structures to gain estimation robustness and modeling flexibility. However, by exploring the modeling structures…
NESTT: A Nonconvex Primal-Dual Splitting Method for Distributed and Stochastic Optimization
Davood Hajinezhad, Mingyi Hong, Tuo Zhao +1
We study a stochastic and distributed algorithm for nonconvex problems whose objective consists of a sum of nonconvex -smooth functions, plus a nonsmooth regularizer. Th…
Nonconvex Sparse Learning via Stochastic Optimization with Progressive Variance Reduction
Xingguo Li, Raman Arora, Han Liu +2
We propose a stochastic variance reduced optimization algorithm for solving sparse learning problems with cardinality constraints. Sufficient conditions are provided, under which t…