Sciweavers

5 search results - page 1 / 1
» Prediction with Expert Advice by Following the Perturbed Lea...
Sort
View
ALT
2004
Springer
14 years 2 months ago
Prediction with Expert Advice by Following the Perturbed Leader for General Weights
When applying aggregating strategies to Prediction with Expert Advice, the learning rate must be adaptively tuned. The natural choice of complexity/current loss renders the analys...
Marcus Hutter, Jan Poland
ALT
2009
Springer
13 years 10 months ago
The Follow Perturbed Leader Algorithm Protected from Unbounded One-Step Losses
In this paper the sequential prediction problem with expert advice is considered for the case when the losses of experts suffered at each step can be unbounded. We present some mo...
Vladimir V. V'yugin
JMLR
2011
137views more  JMLR 2011»
13 years 13 days ago
Online Learning in Case of Unbounded Losses Using Follow the Perturbed Leader Algorithm
In this paper the sequential prediction problem with expert advice is considered for the case where losses of experts suffered at each step cannot be bounded in advance. We presen...
Vladimir V. V'yugin
COLT
2007
Springer
13 years 11 months ago
Learning Permutations with Exponential Weights
We give an algorithm for the on-line learning of permutations. The algorithm maintains its uncertainty about the target permutation as a doubly stochastic weight matrix, and makes...
David P. Helmbold, Manfred K. Warmuth
SIGECOM
2010
ACM
149views ECommerce» more  SIGECOM 2010»
13 years 10 months ago
A new understanding of prediction markets via no-regret learning
We explore the striking mathematical connections that exist between market scoring rules, cost function based prediction markets, and no-regret learning. We first show that any c...
Yiling Chen, Jennifer Wortman Vaughan