A matrix concentration inequality for products
Probability
2020-08-20 v2 Machine Learning
Abstract
We present a non-asymptotic concentration inequality for the random matrix product \begin{equation}\label{eq:Zn} Z_n = \left(I_d-\alpha X_n\right)\left(I_d-\alpha X_{n-1}\right)\cdots \left(I_d-\alpha X_1\right), \end{equation} where is a sequence of bounded independent random positive semidefinite matrices with common expectation . Under these assumptions, we show that, for small enough positive , satisfies the concentration inequality \begin{equation}\label{eq:CTbound} \mathbb{P}\left(\left\Vert Z_n-\mathbb{E}\left[Z_n\right]\right\Vert \geq t\right) \leq 2d^2\cdot\exp\left(\frac{-t^2}{\alpha \sigma^2} \right) \quad \text{for all } t\geq 0, \end{equation} where denotes a variance parameter.
Keywords
Cite
@article{arxiv.2008.05104,
title = {A matrix concentration inequality for products},
author = {Sina Baghal},
journal= {arXiv preprint arXiv:2008.05104},
year = {2020}
}