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

Wenjie Zheng (1) , Aurélien Bellet (2) , Patrick Gallinari (1)

1 MLIA - Machine Learning and Information Access
2 MAGNET - Machine Learning in Information Networks

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.

Mots clés: Frank–Wolfe algorithm; Low-rank learning; Trace norm; Distributed optimization; Multi-task learning; Multinomial logistic regression

Domaines: Apprentissage [cs.LG]; Machine Learning [stat.ML]

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⟩