Sciweavers

12 search results - page 1 / 3
» Lower bounds on individual sequence regret
Sort
View
COLT
2010
Springer
13 years 2 months ago
Following the Flattened Leader
We analyze the regret, measured in terms of log loss, of the maximum likelihood (ML) sequential prediction strategy. This "follow the leader" strategy also defines one o...
Wojciech Kotlowski, Peter Grünwald, Steven de...
IEICET
2006
76views more  IEICET 2006»
13 years 4 months ago
Relationship among Complexities of Individual Sequences over Countable Alphabet
This paper investigates some relations among four complexities of sequence over countably infinite alphabet, and shows that two kinds of empirical entropies and the self-entropy r...
Shigeaki Kuzuoka, Tomohiko Uyematsu
TSP
2008
114views more  TSP 2008»
13 years 4 months ago
Universal Switching Linear Least Squares Prediction
We consider sequential regression of individual sequences under the square error loss. Using a competitive algorithm framework, we construct a sequential algorithm that can achieve...
Suleyman Serdar Kozat, Andrew C. Singer
COLT
2004
Springer
13 years 8 months ago
Minimizing Regret with Label Efficient Prediction
We investigate label efficient prediction, a variant, proposed by Helmbold and Panizza, of the problem of prediction with expert advice. In this variant, the forecaster, after gues...
Nicolò Cesa-Bianchi, Gábor Lugosi, G...
COLT
2010
Springer
13 years 2 months ago
Regret Minimization With Concept Drift
In standard online learning, the goal of the learner is to maintain an average loss that is "not too big" compared to the loss of the best-performing function in a fixed...
Koby Crammer, Yishay Mansour, Eyal Even-Dar, Jenni...