A Vector Bernstein Inequality for Self-Normalized Martingales
Abstract¶
We prove a Bernstein inequality for vector-valued self-normalized martingales. We first give an alternative perspective of the corresponding sub-Gaussian bound due to Abbasi-Yadkori et al. via a PAC-Bayesian argument with Gaussian priors. By instantiating this argument to priors drawn uniformly over well-chosen ellipsoids, we obtain a Bernstein bound.
Links¶
Knowledge Base
External
Similar Papers¶
1
77%
2
76%
3
74%
4
74%
5
73%