Lien 
vers le site de l'ENS
ÉCOLE NORMALE SUPÉRIEUREPARIS
Lien vers l'accueil
lancer la recherche

» Conférences d’après mars 2011 : nouveau site

1434

Journée Mathematical Foundations of Learning Theory

< précédent | suivant >

On Context-tree Prediction of Individual Sequences
Neri Merhav (Technion, I.I.T.)

31 mai 2006

Motivated by the evident success of context–tree based methods in lossless data compression, we explore, in this talk, methods of the same spirit in universal prediction of individual sequences. By context–tree prediction, we refer to a family of prediction schemes, where at each time instant t, after having observed all outcomes of the data sequence x1 , . . . , xt−1 , but not yet xt , the prediction is based on a “context” (or a state) that consists of the k most recent past outcomes xt−k , . . . , xt−1 , where the choice of k may depend on the contents of a possibly longer, though limited, portion of the observed past, xt−kmax , . . . , xt−1 . This is different from the study reported in Feder, Merhav, and Gutman (2002), where general finite–state predictors as well as “Markov” (finite–memory) predictors of fixed order, where studied in the regime of individual sequences.
Another important difference between this study and Feder, Merhav, and Gutman (2002) is the asymptotic regime. While in Feder, Merhav, and Gutman (2002), the resources of the predictor (i.e., the number of states or the memory size) were kept fixed regardless of the length N of the data sequence, here we investigate situations where the number of contexts, or states, is allowed to grow concurrently with N . We are primarily interested in the following fundamental question: What is the critical growth rate of the number of contexts, below which the performance of the best context–tree predictor is still universally achievable, but above which it is not? We show that this critical growth rate is linear in N . In particular, we propose a universal context–tree algorithm that essentially achieves optimum performance as long as the growth rate is sublinear, and show that, on the other hand, this is impossible in the linear case.
Further references

Télécharger
pictogrammeformat pdf - 391.95 Ko

Écouter
pictogrammeformat audio mp3 - ??? (erreur acces)

- Visualiser
- Télécharger
pictogrammeformat quicktime mov, vidéo à la demande

Télécharger
pictogrammeformat mp4, vidéo à télécharger - 101.07 Mo

Télécharger
pictogrammeformat windows media video - 63.14 Mo

Neri Merhav Neri Merhav (Technion, I.I.T.)
Department of Electrical Engineering
Technion - Israel Institute of Technology