Linear Convergence of Stochastic Iterative Greedy Algorithms With Sparse Constraints

DOI10.1109/TIT.2017.2749330zbMATH Open1390.94326arXiv1407.0088OpenAlexW2963297739MaRDI QIDQ4566535FDOQ4566535

Authors:

Publication date: 27 June 2018

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Abstract: Motivated by recent work on stochastic gradient descent methods, we develop two stochastic variants of greedy algorithms for possibly non-convex optimization problems with sparsity constraints. We prove linear convergence in expectation to the solution within a specified tolerance. This generalized framework applies to problems such as sparse signal recovery in compressed sensing, low-rank matrix recovery, and covariance matrix estimation, giving methods with provable convergence guarantees that often outperform their deterministic counterparts. We also analyze the settings where gradients and projections can only be computed approximately, and prove the methods are robust to these approximations. We include many numerical experiments which align with the theoretical analysis and demonstrate these improvements in several different settings.

Full work available at URL: https://arxiv.org/abs/1407.0088

Mathematics Subject Classification ID

Applications of mathematical programming (90C90) Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Stochastic programming (90C15)

Cited In (14)

• Iterative singular tube hard thresholding algorithms for tensor recovery
• Stochastic variance reduced gradient for affine rank minimization problem
• Iterative hard thresholding for low CP-rank tensor models
• A tight bound of hard thresholding
• Stochastic greedy algorithms for multiple measurement vectors
• Improved RIP-based bounds for guaranteed performance of two compressed sensing algorithms
• Title not available (Why is that?)
• Title not available (Why is that?)
• Consistent online Gaussian process regression without the sample complexity bottleneck
• The stochastic proximal distance algorithm
• Stochastic privacy-preserving methods for nonconvex sparse learning
• Title not available (Why is that?)
• Weighted thresholding homotopy method for sparsity constrained optimization
• Decomposable norm minimization with proximal-gradient homotopy algorithm

This page was built for publication: Linear Convergence of Stochastic Iterative Greedy Algorithms With Sparse Constraints

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4566535)