Bo Huang – Optimization Online

Provable Low-Rank Tensor Recovery

Published: 2014/02/26

Convex and Nonsmooth Optimization incoherence condition, low-rank tensor recovery, strongly convex programming, sum of nuclear norms minimization, tensor completion, tensor robust principal component analysis, tucker decomposition

In this paper, we rigorously study tractable models for provably recovering low-rank tensors. Unlike their matrix-based predecessors, current convex approaches for recovering low-rank tensors based on incomplete (tensor completion) and/or grossly corrupted (tensor robust principal analysis) observations still suffer from the lack of theoretical guarantees, although they have been used in various recent applications and … Read more

Accelerated Linearized Bregman Method

Published: 2011/06/27

Bo Huang

Shiqian Ma

Donald Goldfarb

Convex and Nonsmooth Optimization accelerated linearized bregman method, basis pursuit, compressed sensing, convex optimization, linearized bregman method, matrix completion

In this paper, we propose and analyze an accelerated linearized Bregman (ALB) method for solving the basis pursuit and related sparse optimization problems. This accelerated algorithm is based on the fact that the linearized Bregman (LB) algorithm is equivalent to a gradient descent method applied to a certain dual formulation. We show that the LB … Read more