Cesana Arlotti, Nicolò, 1981-Lugosi, GáborUniversitat Pompeu Fabra. Departament d'Economia i Empresa2017-07-262017-07-261999-10-01Machine Learning, 43, 3, (2001), pp. 247-264http://hdl.handle.net/10230/934We investigate on-line prediction of individual sequences. Given a class of predictors, the goal is to predict as well as the best predictor in the class, where the loss is measured by the self information (logarithmic) loss function. The excess loss (regret) is closely related to the redundancy of the associated lossless universal code. Using Shtarkov's theorem and tools from empirical process theory, we prove a general upper bound on the best possible (minimax) regret. The bound depends on certain metric properties of the class of predictors. We apply the bound to both parametric and nonparametric classes of predictors. Finally, we point out a suboptimal behavior of the popular Bayesian weighted average algorithm.application/pdfengL'accés als continguts d'aquest document queda condicionat a l'acceptació de les condicions d'ús establertes per la següent llicència Creative Commonsinfo:eu-repo/semantics/workingPaperuniversal predictionuniversal codingempirical processeson-line learningmetric entropyStatistics, Econometrics and Quantitative Methodsinfo:eu-repo/semantics/openAccess