Approximating Subdifferentials by Random Sampling of Gradients

DOI10.1287/moor.27.3.567.317zbMath1082.49019MaRDI QIDQ5704097

Michael L. Overton, James V. Burke, Adrian S. Lewis

Publication date: 11 November 2005

Published in: Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL: https://semanticscholar.org/paper/701542fb24a91fc57a85253458271c56581e398a

zbMATH Keywords

nonsmooth analysis; eigenvalue optimization; spectral abscissa; Clarke subdifferential; bundle method; generalized gradient; stochastic gradient

Mathematics Subject Classification ID

49J52: Nonsmooth analysis

Related Items

Differentiability of cone-monotone functions on separable Banach space, Derivative-free optimization methods for finite minimax problems, Non-convex multiobjective optimization under uncertainty: a descent algorithm. Application to sandwich plate design and reliability, A New Sequential Optimality Condition for Constrained Nonsmooth Optimization, Manifold Sampling for Optimizing Nonsmooth Nonconvex Compositions, Subsampling Algorithms for Semidefinite Programming, A splitting bundle approach for non-smooth non-convex minimization, Clarke Subgradients for Directionally Lipschitzian Stratifiable Functions, An Improved Unconstrained Approach for Bilevel Optimization, \(\varepsilon\)-subgradient algorithms for locally Lipschitz functions on Riemannian manifolds, Semi-algebraic functions have small subdifferentials, A derivative-free approximate gradient sampling algorithm for finite minimax problems, The dimension of semialgebraic subdifferential graphs, On Nesterov's nonsmooth Chebyshev-Rosenbrock functions, Generalized derivatives and nonsmooth optimization, a finite dimensional tour (with comments and rejoinder), A note on an approximate Lagrange multiplier rule, A quasi-Newton algorithm for nonconvex, nonsmooth optimization with global convergence guarantees, Two numerical methods for optimizing matrix stability, Constraint qualifications and stationary conditions for mathematical programming with non-differentiable vanishing constraints, Descent algorithm for nonsmooth stochastic multiobjective optimization, Nonsmooth spectral gradient methods for unconstrained optimization, A fast gradient and function sampling method for finite-max functions, Local minimizers of the Crouzeix ratio: a nonsmooth optimization case study, Convergence of the gradient sampling algorithm on directionally Lipschitz functions, Perturbed iterate SGD for Lipschitz continuous loss functions, An inexact restoration-nonsmooth algorithm with variable accuracy for stochastic nonsmooth convex optimization problems in machine learning and stochastic linear complementarity problems, Spectral radius minimization for optimal average consensus and output feedback stabilization, Softness, sleekness and regularity properties in nonsmooth analysis, On the convergence analysis of a penalty algorithm for nonsmooth optimization and its performance for solving hard-sphere problems, Spectral projected subgradient method for nonsmooth convex optimization problems, A Subgradient Method Based on Gradient Sampling for Solving Convex Optimization Problems, On the differentiability check in gradient sampling methods, An adaptive gradient sampling algorithm for non-smooth optimization, On the nondifferentiability of cone-monotone functions in Banach spaces, A nonsmooth optimisation approach for the stabilisation of time-delay systems