Sciweavers

125 search results - page 8 / 25
» The Stochastic Machine Replenishment Problem
Sort
View
ALT
1999
Springer
14 years 2 months ago
Extended Stochastic Complexity and Minimax Relative Loss Analysis
We are concerned with the problem of sequential prediction using a givenhypothesis class of continuously-manyprediction strategies. An e ectiveperformance measure is the minimax re...
Kenji Yamanishi
ALT
2007
Springer
14 years 6 months ago
Tuning Bandit Algorithms in Stochastic Environments
Algorithms based on upper-confidence bounds for balancing exploration and exploitation are gaining popularity since they are easy to implement, efficient and effective. In this p...
Jean-Yves Audibert, Rémi Munos, Csaba Szepe...
CIAC
2010
Springer
259views Algorithms» more  CIAC 2010»
14 years 1 months ago
On Strategy Improvement Algorithms for Simple Stochastic Games
The study of simple stochastic games (SSGs) was initiated by Condon for analyzing the computational power of randomized space-bounded alternating Turing machines. The game is play...
Rahul Tripathi, Elena Valkanova, V. S. Anil Kumar
JMLR
2010
123views more  JMLR 2010»
13 years 4 months ago
Inductive Principles for Restricted Boltzmann Machine Learning
Recent research has seen the proposal of several new inductive principles designed specifically to avoid the problems associated with maximum likelihood learning in models with in...
Benjamin Marlin, Kevin Swersky, Bo Chen, Nando de ...
ALT
2008
Springer
13 years 11 months ago
Some Sufficient Conditions on an Arbitrary Class of Stochastic Processes for the Existence of a Predictor
Abstract. We consider the problem of sequence prediction in a probabilistic setting. Let there be given a class C of stochastic processes (probability measures on the set of one-wa...
Daniil Ryabko