General multilevel adaptations for stochastic approximation algorithms

2019/12/17 by Dereich, Steffen · 1 citation
#FOS: Mathematics #Probability (math.PR)

paper · doi:10.48550/arxiv.1912.08130

Abstract

In this article we establish central limit theorems for multilevel Polyak-Ruppert averaged stochastic approximation schemes. We work under very mild technical assumptions and consider the slow regime in wich typical errors decay like N^-δ with δ∈(0,\frac 12) and the critical regime in which errors decay of order N^-1/2√(log N) in the runtime N of the algorithm.

Cited by

• PADAM: Parallel averaged Adam reduces the error for stochastic optimization in scientific machine learning

Related

• General multilevel adaptations for stochastic approximation algorithms
• Limit theorems for stochastic approximation algorithms
• Improved Central Limit Theorem and Bootstrap Approximations for Linear Stochastic Approximation
• Nonasymptotic CLT and Error Bounds for Two-Time-Scale Stochastic Approximation
• Multi-level stochastic approximation algorithms