A general nonconvex large deviation result II

2004/07/01 by A. de Acosta
Computer Science · Decision Sciences · Economics, Econometrics and Finance · Mathematics · #Risk and Portfolio Optimization #Stochastic Gradient Optimization Techniques #Stochastic processes and financial applications #math.PR #msc:60F10.

paper · pdf · doi:10.1214/009117904000000441

published as Annals of Probability 2004, Vol. 32, No. 3A, 1873-1901 · Published by the Institute of Mathematical Statistics (http://www.imstat.org) in the Annals of Probability (http://www.imstat.org/aop/) at http://dx.doi.org/10.1214/009117904000000441

openalex publication_date 2004/07/01 · arxiv created 2004/10/05 · arxiv updated 2009/12/01 · openalex created_date 2016/06/24 · openalex updated_date 2026/07/28

Abstract

We refine the conditions for the lower bound in an abstract large deviation result with nonconvex rate function we had previously introduced. We apply the results to certain stochastic recursive schemes.

Related

• Some Refinements of Large Deviation Tail Probabilities
• Two examples of non strictly convex large deviations
• A weak convergence approach to large deviations for stochastic approximations
• Large deviations for possibly reducible Markov chains on discrete state spaces
• Nonlinear large deviations