A Distributed Frank-Wolfe Framework for Learning Low-Rank Matrices with the Trace Norm - Archive ouverte HAL Access content directly
Journal Articles Machine Learning Year : 2018

A Distributed Frank-Wolfe Framework for Learning Low-Rank Matrices with the Trace Norm

(1) , (2) , (1)
1
2

Abstract

We consider the problem of learning a high-dimensional but low-rank matrix from a large-scale dataset distributed over several machines, where low-rankness is enforced by a convex trace norm constraint. We propose DFW-Trace, a distributed Frank-Wolfe algorithm which leverages the low-rank structure of its updates to achieve efficiency in time, memory and communication usage. The step at the heart of DFW-Trace is solved approximately using a distributed version of the power method. We provide a theoretical analysis of the convergence of DFW-Trace, showing that we can ensure sublinear convergence in expectation to an optimal solution with few power iterations per epoch. We implement DFW-Trace in the Apache Spark distributed programming framework and validate the usefulness of our approach on synthetic and real data, including the ImageNet dataset with high-dimensional features extracted from a deep neural network.
Fichier principal
Vignette du fichier
mlj18.pdf (520.59 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01922994 , version 1 (14-11-2018)

Identifiers

Cite

Wenjie Zheng, Aurélien Bellet, Patrick Gallinari. A Distributed Frank-Wolfe Framework for Learning Low-Rank Matrices with the Trace Norm. Machine Learning, 2018, ⟨10.1007/s10994-018-5713-5⟩. ⟨hal-01922994⟩
103 View
71 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More