Paper #324

Title:

On prediction of individual sequences

Authors:

Nicolo Cesa Bianchi and Gábor Lugosi

Date:

July 1998

Abstract:

Sequential randomized prediction of an arbitrary binary sequence is investigated. No assumption is made on the mechanism of generating the bit sequence. The goal of the predictor is to minimize its relative loss, i.e., to make (almost) as few mistakes as the best ``expert'' in a fixed, possibly infinite, set of experts. We point out a surprising connection between this prediction problem and empirical process theory. First, in the special case of static (memoryless) experts, we completely characterize the minimax relative loss in terms of the maximum of an associated Rademacher process. Then we show general upper and lower bounds on the minimax relative loss in terms of the geometry of the class of experts. As main examples, we determine the exact order of magnitude of the minimax relative loss for the class of autoregressive linear predictors and for the class of Markov experts.

Keywords:

Universal prediction, prediction with experts, absolute loss, empirical processes, covering numbers, finite-state machines

JEL codes:

C20, G25

Area of Research:

Statistics, Econometrics and Quantitative Methods

Published in:

Annals of Statistics, 27, 6, (1999), 1865-1895

Download the paper in PDF format