Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
Worst Case Prediction over Sequences under Log Loss
Ist Teil von
The Mathematics of Information Coding, Extraction and Distribution, p.81-90
Ort / Verlag
New York, NY: Springer New York
Link zum Volltext
Quelle
Alma/SFX Local Collection
Beschreibungen/Notizen
We consider the game of sequentially assigning probabilities to future data based on past observations under logarithmic loss. We are not making probabilistic assumptions about the generation of the data, but consider a situation where a player tries to minimize his loss relative to the loss of the (with hindsight) best distribution from a target class for the worst sequence of data. We give bounds on the minimax regret in terms of the metric entropies of the target class with respect to suitable distances between distributions.