Supervision : Patrick GALLINARI

A Distributed Frank–Wolfe Framework for Trace Norm Minimization via the Bulk Synchronous Parallel Model

Learning low-rank matrices is a problem of great importance in statistics, machine learning, computer vision, recommender systems, etc. Because of its NP-hard nature, a principled approach is to solve its tightest convex relaxation: trace norm minimization. Among various algorithms capable of solving this optimization is the Frank-Wolfe method, which is particularly suitable for high-dimensional matrices. In preparation for the usage of distributed infrastructures to further accelerate the computation, this study aims at exploring the possibility of executing the Frank-Wolfe algorithm in a star network with the Bulk Synchronous Parallel (BSP) model and investigating its efficiency both theoretically and empirically.

2017-2018 Publications

• 2018
  • W. Zheng : “A Distributed Frank–Wolfe Framework for Trace Norm Minimization via the Bulk Synchronous Parallel Model”, thesis, phd defence 06/13/2018, supervision Gallinari, Patrick (2018)
  • W. Zheng, A. Bellet, P. Gallinari : “A Distributed Frank-Wolfe Framework for Learning Low-Rank Matrices with the Trace Norm”, Machine Learning, (Springer Verlag) (2018)
• 2017
  • W. Zheng, A. Bellet, P. Gallinari : “A Distributed Frank-Wolfe Framework for Learning Low-Rank Matrices with the Trace Norm”, 1-19 pages (2017)