72 citations · 542 across the 65 of their papers we have counts for
6 papers · 1 filter
Momentum-inspired Low-Rank Coordinate Descent for Diagonally Constrained SDPs
Junhyung Lyle Kim, JA Lara Benitez, Mohammad Taha Toghani +3
We present a novel, practical, and provable approach for solving diagonally constrained semi-definite programming (SDP) problems at scale using accelerated non-convex programming.…
IHT dies hard: Provable accelerated Iterative Hard Thresholding
Rajiv Khanna, Anastasios Kyrillidis
We study --both in theory and practice-- the use of momentum motions in classic iterative hard thresholding (IHT) methods. By simply modifying plain IHT, we investigate its converg…
Finding Low-Rank Solutions via Non-Convex Matrix Factorization, Efficiently and Provably
Dohyung Park, Anastasios Kyrillidis, Constantine Caramanis +1
A rank- matrix can be written as a product , where and . One could explo…
A single-phase, proximal path-following framework
Quoc Tran-Dinh, Anastasios Kyrillidis, Volkan Cevher
We propose a new proximal, path-following framework for a class of constrained convex problems. We consider settings where the nonlinear---and possibly non-smooth---objective part…
An Inexact Proximal Path-Following Algorithm for Constrained Convex Minimization
Quoc Tran Dinh, Anastasios Kyrillidis, Volkan Cevher
Many scientific and engineering applications feature nonsmooth convex minimization problems over convex sets. In this paper, we address an important instance of this broad class wh…
Randomized Low-Memory Singular Value Projection
Stephen Becker, Volkan Cevher, Anastasios Kyrillidis
Affine rank minimization algorithms typically rely on calculating the gradient of a data error followed by a singular value decomposition at every iteration. Because these two step…