Year: 2016
Type: preprint
Abstract: We propose a stochastic variance reduced optimization algorithm for solving sparse learning problems with cardinality constraints. Sufficient conditions are provided, under which the proposed algorithm enjoys strong linear convergence guarantees and optimal estimation accuracy in high dimensions. We further extend the proposed algorithm to an asynchronous parallel variant with a near linear speedup. Numerical experiments demonstrate the efficiency of our algorithm in terms of both parameter estimation and computational performance.
Source: arXiv (Cornell University)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: BIGDATA: Collaborative Research: F: Stochastic Approximation for Subspace and Multiview Representation Learning, Spectral Tweets: A Community Paradigm for Spatio-temporal Cognitive Sensing and Access, CAREER: An Integrated Inferential Framework for Big Data Research and Education, III: Small: Nonparametric Structure Learning for Complex Scientific Datasets, G7183873188, RI: Medium: Collaborative Research: Next-Generation Statistical Optimization Methods for Big Data Computing, CIF: Small: Beyond Sparsity - Exploiting Saliency in Compressive and Adaptive Sensing
OpenAlex ID: W2554489331
