SPRING: A fast stochastic proximal alternating method for non-smooth non-convex optimization

Derek Driggs, Junqi Tang, Jingwei Liang, Mike Davies, Carola-Bibiane Schönlieb

Research output: Working paper

Abstract / Description of output

We introduce SPRING, a novel stochastic proximal alternating linearized minimization algorithm for solving a class of non-smooth and non-convex optimization problems. Large-scale imaging problems are becoming increasingly prevalent due to advances in data acquisition and computational capabilities. Motivated by the success of stochastic optimization methods, we propose a stochastic variant of proximal alternating linearized minimization (PALM) algorithm \cite{bolte2014proximal}. We provide global convergence guarantees, demonstrating that our proposed method with variance-reduced stochastic gradient estimators, such as SAGA \cite{SAGA} and SARAH \cite{sarah}, achieves state-of-the-art oracle complexities. We also demonstrate the efficacy of our algorithm via several numerical examples including sparse non-negative matrix factorization, sparse principal component analysis, and blind image deconvolution.
Original languageUndefined/Unknown
Number of pages39
Publication statusPublished - 27 Feb 2020

Keywords / Materials (for Non-textual outputs)

  • math.OC
  • 90C26

Cite this