Paper ID | MLSP-14.5 | ||
Paper Title | GEOM-SPIDER-EM: FASTER VARIANCE REDUCED STOCHASTIC EXPECTATION MAXIMIZATION FOR NONCONVEX FINITE-SUM OPTIMIZATION | ||
Authors | Gersende Fort, Institut de Mathématiques de Toulouse, CNRS, France; Eric Moulines, CMAP, Ecole Polytechnique, France; Hoi-To Wai, The Chinese University of Hong-Kong, Hong Kong SAR China | ||
Session | MLSP-14: Learning Algorithms 1 | ||
Location | Gather.Town | ||
Session Time: | Wednesday, 09 June, 13:00 - 13:45 | ||
Presentation Time: | Wednesday, 09 June, 13:00 - 13:45 | ||
Presentation | Poster | ||
Topic | Machine Learning for Signal Processing: [MLR-LEAR] Learning theory and algorithms | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | The Expectation Maximization (EM) algorithm is a key reference for inference in latent variable models; unfortunately, its computational cost is prohibitive in the large scale learning setting. In this paper, we propose an extension of the Stochastic Path-Integrated Differential EstimatoR EM (SPIDER-EM) and derive complexity bounds for this novel algorithm, designed to solve smooth nonconvex finite-sum optimization problems. We show that it reaches the same state of the art complexity bounds as SPIDER-EM; and provide conditions for a linear rate of convergence. Numerical results support our findings. |