Stochastic Variance Reduced Optimization for Nonconvex Sparse Learning

We propose a stochastic variance reduced optimization algorithm for solving a class of large-scale nonconvex optimization problems with cardinality constraints, and provide sufficient conditions under which the proposed algorithm enjoys strong linear convergence guarantees and optimal estimation accuracy in high dimensions. Numerical experiments demonstrate the efficiency of our method in terms of both parameter estimation and computational performance.

Authors

• Xingguo Li
• Tuo Zhao
• Raman Arora
• Han Liu 0001
• Jarvis D. Haupt

Keywords

No keywords are indexed for this paper.