Title :
On Semi-Probabilistic universal prediction
Author :
Rakhlin, Alexander ; Sridharan, K.
Author_Institution :
Dept. of Stat., Univ. of Pennsylvania, Philadelphia, PA, USA
Abstract :
We discuss two scenarios of universal prediction, as well as some recent advances in the study of minimax regret and algorithmic development. We then propose an intermediate scenario, the Semi-Probabilistic Setting, and make progress towards understanding the associated minimax regret.
Keywords :
minimax techniques; probability; algorithmic development; minimax regret; semiprobabilistic universal prediction; Complexity theory; Loss measurement; Prediction algorithms; Prediction methods; Probabilistic logic; Statistical learning; Upper bound;
Conference_Titel :
Information Theory Workshop (ITW), 2013 IEEE
Conference_Location :
Sevilla
Print_ISBN :
978-1-4799-1321-3
DOI :
10.1109/ITW.2013.6691289
