Efficient Gradient Support Pursuit With Less Hard Thresholding for Cardinality-Constrained Learning.
Sign Up to like & getrecommendations! Published in 2021 at "IEEE transactions on neural networks and learning systems"
DOI: 10.1109/tnnls.2021.3087805
Abstract: Recently, stochastic hard thresholding (HT) optimization methods [e.g., stochastic variance reduced gradient hard thresholding (SVRGHT)] are becoming more attractive for solving large-scale sparsity/rank-constrained problems. However, they have much higher HT oracle complexities, especially for high-dimensional… read more here.
Keywords: gradient support; hard thresholding; support pursuit; stochastic variance ... See more keywords
Variable metric proximal stochastic variance reduced gradient methods for nonconvex nonsmooth optimization
Sign Up to like & getrecommendations! Published in 2021 at "Journal of Industrial and Management Optimization"
DOI: 10.3934/jimo.2021084
Abstract: We study the problem of minimizing the sum of two functions. The first function is the average of a large number of nonconvex component functions and the second function is a convex (possibly nonsmooth) function… read more here.
Keywords: stochastic variance; variance reduced; proximal stochastic; variable metric ... See more keywords