DeepAI AI Chat
Log In Sign Up

Tight High Probability Bounds for Linear Stochastic Approximation with Fixed Stepsize

by   Alain Durmus, et al.

This paper provides a non-asymptotic analysis of linear stochastic approximation (LSA) algorithms with fixed stepsize. This family of methods arises in many machine learning tasks and is used to obtain approximate solutions of a linear system A̅θ = b̅ for which A̅ and b̅ can only be accessed through random estimates {( A_n, b_n): n ∈ℕ^*}. Our analysis is based on new results regarding moments and high probability bounds for products of matrices which are shown to be tight. We derive high probability bounds on the performance of LSA under weaker conditions on the sequence {( A_n, b_n): n ∈ℕ^*} than previous works. However, in contrast, we establish polynomial concentration bounds with order depending on the stepsize. We show that our conclusions cannot be improved without additional assumptions on the sequence of random matrices { A_n: n ∈ℕ^*}, and in particular that no Gaussian or exponential high probability bounds can hold. Finally, we pay a particular attention to establishing bounds with sharp order with respect to the number of iterations and the stepsize and whose leading terms contain the covariance matrices appearing in the central limit theorems.


page 1

page 2

page 3

page 4


Finite-time High-probability Bounds for Polyak-Ruppert Averaged Iterates of Linear Stochastic Approximation

This paper provides a finite-time analysis of linear stochastic approxim...

The Lanczos Algorithm Under Few Iterations: Concentration and Location of the Ritz Values

We study the Lanczos algorithm where the initial vector is sampled unifo...

Probabilistic analysis of Wiedemann's algorithm for minimal polynomial computation

Blackbox algorithms for linear algebra problems start with projection of...

High Probability Convergence for Accelerated Stochastic Mirror Descent

In this work, we describe a generic approach to show convergence with hi...

Concentration of Random Feature Matrices in High-Dimensions

The spectra of random feature matrices provide essential information on ...

Linear and Fisher Separability of Random Points in the d-dimensional Spherical Layer

Stochastic separation theorems play important role in high-dimensional d...

Approximating the Permanent by Sampling from Adaptive Partitions

Computing the permanent of a non-negative matrix is a core problem with ...