In this paper, we derive exponential bounds on probabilities of large deviations for “light tail” martingales taking values in finite-dimensional normed spaces. Our primary emphasis is on the case where the bounds are dimension-independent or nearly so. We demonstrate that this is the case when the norm on the space can be approximated, within an absolute constant factor, by a norm which is differentiable on the unit sphere with a Lipschitz continuous %, with a given constant, gradient. We also present various examples of spaces possessing the latter property.
Citation
Preprint, ISyE, Georgia Institute of Technology, 765 Ferst Dr. NW Atlanta GA 30332-0205