Deviation inequalities for stochastic approximation by averaging
Preprint
Abstract
We introduce a class of Markov chains, that contains the model of stochastic approximation by averaging and non-averaging. Using martingale approximation method, we establish various deviation inequalities for separately Lipschitz functions of such a chain, with different moment conditions on some dominating random variables of martingale differences.Finally, we apply these inequalities to the stochastic approximation by averaging and empirical risk minimisation.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- High-dimensional VAR with low-rank transitionStatistics and Computing, 2020
- Deviation inequalities for separately Lipschitz functionals of composition of random functionsJournal of Mathematical Analysis and Applications, 2019
- Deviation inequalities for martingales with applicationsJournal of Mathematical Analysis and Applications, 2017
- Deviation inequalities for separately Lipschitz functionals of iterated random functionsStochastic Processes and their Applications, 2015
- Fast learning from-mixing observationsJournal of Multivariate Analysis, 2014
- A Bernstein type inequality and moderate deviations for weakly dependent sequencesProbability Theory and Related Fields, 2010
- Moment Inequalities for Sums of Dependent Random Variables under Projective ConditionsJournal of Theoretical Probability, 2008
- Limit Theory for Moderate Deviations From a Unit Root Under Weak Dependence2007
- Nonparametric Time Series Prediction Through Adaptive Model SelectionMachine Learning, 2000
- Acceleration of Stochastic Approximation by AveragingSIAM Journal on Control and Optimization, 1992