Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published July 2017 | Published + Accepted Version
Journal Article Open

Homotopy Analysis for Tensor PCA

Abstract

Developing efficient and guaranteed nonconvex algorithms has been an important challenge in modern machine learning. Algorithms with good empirical performance such as stochastic gradient descent often lack theoretical guarantees. In this paper, we analyze the class of homotopy or continuation methods for global optimization of nonconvex functions. These methods start from an objective function that is efficient to optimize (e.g. convex), and progressively modify it to obtain the required objective, and the solutions are passed along the homotopy path. For the challenging problem of tensor PCA, we prove global convergence of the homotopy method in the "high noise" regime. The signal-to-noise requirement for our algorithm is tight in the sense that it matches the recovery guarantee for the \em best degree-4 sum-of-squares algorithm. In addition, we prove a phase transition along the homotopy path for tensor PCA. This allows us to simplify the homotopy method to a local search algorithm, viz., tensor power iterations, with a specific initialization and a noise injection procedure, while retaining the theoretical guarantees.

Additional Information

© 2017 A. Anandkumar, Y. Deng, R. Ge & H. Mobahi.

Attached Files

Published - anandkumar17a.pdf

Accepted Version - 1610.09322.pdf

Files

1610.09322.pdf
Files (2.2 MB)
Name Size Download all
md5:78dcaa04872bd72a87c760343a1910f3
918.9 kB Preview Download
md5:87e20849f39343ce78128dba695800ef
1.3 MB Preview Download

Additional details

Created:
August 19, 2023
Modified:
October 20, 2023