Do stochastic algorithms avoid traps?

zbMath0849.62043MaRDI QIDQ1917693

Marie Duflo, Odile Brandière

Publication date: 27 October 1996

Published in: Annales de l'Institut Henri Poincaré. Probabilités et Statistiques (Search for Journal in Brave)

Full work available at URL: http://www.numdam.org/item?id=AIHPB_1996__32_3_395_0

zbMATH Keywords

local minimaregression modelsprincipal componentsgradient algorithmdifferential equation methodstochastic gradient algorithmRobbins-Monro algorithmKiefer-Wolfowitz algorithmGibbsian modelMarkov perturbationsrepulsive direction

Mathematics Subject Classification ID

Stochastic approximation (62L20) Limit theorems in probability theory (60F99)

Related Items

When can the two-armed bandit algorithm be trusted?, Sur quelques algorithmes récursifs pour les probabilités numériques, Vertex-reinforced random walks and a conjecture of Pemantle, Convergence rates for annealing diffusion processes, A space quantization method for numerical integration, Risk-Sensitive Reinforcement Learning via Policy Gradient Search, Heterogeneous beliefs and local information in stochastic fictitious play, On maximum a posteriori estimation with Plug \& Play priors and stochastic gradient descent, Stochastic heavy ball, Widening the scope of an eigenvector stochastic approximation process and application to streaming PCA and related methods, Stochastic optimization with momentum: convergence, fluctuations, and traps avoidance, Stochastic approximation, cooperative dynamics and supermodular games, Recursive estimation for ordered eigenvectors of symmetric matrix with observation noise, Unnamed Item, Nonlinear randomized urn models: a stochastic approximation viewpoint, On the convergence of reinforcement learning, Avoidance of traps in stochastic approximation, The actor-critic algorithm as multi-time-scale stochastic approximation., Stochastic approximation algorithms: overview and recent trends., Convergence of a stochastic approximation version of the EM algorithm, Sharp convergence rates of stochastic approximation for degenerate roots, Mixed equilibria and dynamical systems arising from fictitious play in perturbed games, An Adjusted Payoff-Based Procedure for Normal Form Games, Strongly vertex-reinforced jump process on a complete graph, Importance sampling for families of distributions, Stochastic approximation algorithms with constant step size whose average is cooperative, Weak convergence rates for stochastic approximation with application to multiple targets and simulated annealing, Piecewise constant triangular cooling schedules for generalized simulated annealing algorithms, Weak dependence beyond mixing and asymptotics for nonparametric regression