DeepAI AI Chat
Log In Sign Up

On Riemannian Stochastic Approximation Schemes with Fixed Step-Size

by   Alain Durmus, et al.

This paper studies fixed step-size stochastic approximation (SA) schemes, including stochastic gradient schemes, in a Riemannian framework. It is motivated by several applications, where geodesics can be computed explicitly, and their use accelerates crude Euclidean methods. A fixed step-size scheme defines a family of time-homogeneous Markov chains, parametrized by the step-size. Here, using this formulation, non-asymptotic performance bounds are derived, under Lyapunov conditions. Then, for any step-size, the corresponding Markov chain is proved to admit a unique stationary distribution, and to be geometrically ergodic. This result gives rise to a family of stationary distributions indexed by the step-size, which is further shown to converge to a Dirac measure, concentrated at the solution of the problem at hand, as the step-size goes to 0. Finally, the asymptotic rate of this convergence is established, through an asymptotic expansion of the bias, and a central limit theorem.


page 1

page 2

page 3

page 4


(Non-) asymptotic properties of Stochastic Gradient Langevin Dynamics

Applying standard Markov chain Monte Carlo (MCMC) algorithms to large da...

On Linear Stochastic Approximation: Fine-grained Polyak-Ruppert and Non-Asymptotic Concentration

We undertake a precise study of the asymptotic and non-asymptotic proper...

The Proxy Step-size Technique for Regularized Optimization on the Sphere Manifold

We give an effective solution to the regularized optimization problem g ...

On the Ergodicity, Bias and Asymptotic Normality of Randomized Midpoint Sampling Method

The randomized midpoint method, proposed by [SL19], has emerged as an op...

The ODE Method for Asymptotic Statistics in Stochastic Approximation and Reinforcement Learning

The paper concerns convergence and asymptotic statistics for stochastic ...

Splitting schemes for second order approximations of piecewise-deterministic Markov processes

Numerical approximations of piecewise-deterministic Markov processes bas...