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

From MaRDI portal
Publication:2896073

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




Related Items (23)

Combination of steepest descent and BFGS methods for nonconvex nonsmooth optimizationOSGA: a fast subgradient algorithm with optimal complexityA note on computing the smallest conic singular valueA Variable Sample-Size Stochastic Quasi-Newton Method for Smooth and Nonsmooth Stochastic Convex OptimizationAn overview of stochastic quasi-Newton methods for large-scale machine learningAn anytime algorithm for constrained stochastic shortest path problems with deterministic policiesConjugate gradient type methods for the nondifferentiable convex minimizationMinimizing oracle-structured composite functionsLine Search Algorithms for Locally Lipschitz Functions on Riemannian ManifoldsSpectral projected subgradient method for nonsmooth convex optimization problemsOn the application of iterative methods of nondifferentiable optimization to some problems of approximation theoryTraining Lp norm multiple kernel learning in the primalNonmonotone Barzilai-Borwein gradient algorithm for \(\ell_1\)-regularized nonsmooth minimization in compressive sensingParallel Optimization Techniques for Machine LearningIMRO: A Proximal Quasi-Newton Method for Solving $\ell_1$-Regularized Least Squares ProblemsUnnamed ItemA fast quasi-Newton method for semi-supervised SVMAn extended Newton-type algorithm for \(\ell_2\)-regularized sparse logistic regression and its efficiency for classifying large-scale datasetsConvergence Rates for Deterministic and Stochastic Subgradient Methods without Lipschitz ContinuityOn Quasi-Newton Forward-Backward Splitting: Proximal Calculus and ConvergenceAdaptive FISTA for Nonconvex OptimizationAn Inexact Semismooth Newton Method on Riemannian Manifolds with Application to Duality-Based Total Variation DenoisingAn 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