Run-and-inspect method for nonconvex optimization and global optimality bounds for R-local minimizers

DOI10.1007/s10107-019-01397-wzbMath1415.90085arXiv1711.08172OpenAlexW2963085159WikidataQ127963668 ScholiaQ127963668MaRDI QIDQ2425163

Wotao Yin, Yuejiao Sun, Yi-Fan Chen

Publication date: 26 June 2019

Published in: Mathematical Programming. Series A. Series B (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1711.08172

zbMATH Keywords

nonconvex optimizationglobal minimumglobal optimalityR-local minimizerrun-and-inspect method

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Nonconvex programming, global optimization (90C26) Nonlinear programming (90C30)

Uses Software

• car
• GAITA
• Entropy-SGD

Cites Work

• Unnamed Item
• Optimization by Simulated Annealing
• Nearly unbiased variable selection under minimax concave penalty
• Accelerated gradient methods for nonconvex nonlinear and stochastic programming
• GAITA: a Gauss-Seidel iterative thresholding algorithm for \(\ell_q\) regularized least squares regression
• Stochastic backward Euler: an implicit gradient descent algorithm for \(k\)-means clustering
• Cubic-regularization counterpart of a variable-norm trust-region method for unconstrained minimization
• Coordinate-friendly structures, algorithms and applications
• Global convergence of ADMM in nonconvex nonsmooth optimization
• Deep relaxation: partial differential equations for optimizing deep neural networks
• Cubic regularization of Newton method and its global performance
• A Block Coordinate Descent Method for Regularized Multiconvex Optimization with Applications to Nonnegative Tensor Factorization and Completion
• Introduction to Derivative-Free Optimization
• Trust Region Methods
• Nonconvex Sparse Logistic Regression With Weakly Convex Regularization
• Gradient Descent Only Converges to Minimizers: Non-Isolated Critical Points and Invariant Regions
• Entropy-SGD: biasing gradient descent into wide valleys