A Quasi-Newton Approach to Nonsmooth Convex Optimization Problems in Machine Learning

zbMath1242.90296arXiv0804.3835MaRDI QIDQ2896073

Jin Yu, S. Günter, Nicol N. Schraudolph, S. V. N. Vishwanathan

Publication date: 13 July 2012

Full work available at URL: https://arxiv.org/abs/0804.3835

variable metric methods subgradient bundle methods risk minimization Wolfe conditions BFGS multiclass multilabel hinge loss BMRM OCAS OWL-QN

Mathematics Subject Classification ID

Abstract computational complexity for mathematical programming problems (90C60) Nonconvex programming, global optimization (90C26) Learning and adaptive systems in artificial intelligence (68T05) Methods of quasi-Newton type (90C53)

Related Items (23)

Combination of steepest descent and BFGS methods for nonconvex nonsmooth optimization ⋮ OSGA: a fast subgradient algorithm with optimal complexity ⋮ A note on computing the smallest conic singular value ⋮ A Variable Sample-Size Stochastic Quasi-Newton Method for Smooth and Nonsmooth Stochastic Convex Optimization ⋮ An overview of stochastic quasi-Newton methods for large-scale machine learning ⋮ An anytime algorithm for constrained stochastic shortest path problems with deterministic policies ⋮ Conjugate gradient type methods for the nondifferentiable convex minimization ⋮ Minimizing oracle-structured composite functions ⋮ Line Search Algorithms for Locally Lipschitz Functions on Riemannian Manifolds ⋮ Spectral projected subgradient method for nonsmooth convex optimization problems ⋮ On the application of iterative methods of nondifferentiable optimization to some problems of approximation theory ⋮ Training Lp norm multiple kernel learning in the primal ⋮ Nonmonotone Barzilai-Borwein gradient algorithm for $\ell_1$-regularized nonsmooth minimization in compressive sensing ⋮ Parallel Optimization Techniques for Machine Learning ⋮ IMRO: A Proximal Quasi-Newton Method for Solving $\ell_1$-Regularized Least Squares Problems ⋮ Unnamed Item ⋮ A fast quasi-Newton method for semi-supervised SVM ⋮ An extended Newton-type algorithm for $\ell_2$-regularized sparse logistic regression and its efficiency for classifying large-scale datasets ⋮ Convergence Rates for Deterministic and Stochastic Subgradient Methods without Lipschitz Continuity ⋮ On Quasi-Newton Forward-Backward Splitting: Proximal Calculus and Convergence ⋮ Adaptive FISTA for Nonconvex Optimization ⋮ An Inexact Semismooth Newton Method on Riemannian Manifolds with Application to Duality-Based Total Variation Denoising ⋮ An inexact restoration-nonsmooth algorithm with variable accuracy for stochastic nonsmooth convex optimization problems in machine learning and stochastic linear complementarity problems

Uses Software

This page was built for publication: A Quasi-Newton Approach to Nonsmooth Convex Optimization Problems in Machine Learning