Paper #324

Títol:

On prediction of individual sequences

Autors:

Nicolo Cesa Bianchi i Gábor Lugosi

Data:

Juliol 1998

Resum:

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.

Paraules clau:

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

Codis JEL:

C20, G25

Àrea de Recerca:

Estadística, Econometria i Mètodes Quantitatius

Publicat a:

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

Descarregar el paper en format PDF