Sciweavers

12 search results - page 2 / 3
» Finite-time Analysis of the Multiarmed Bandit Problem
Sort
View
194
Voted

Publication
466views
16 years 2 months ago
Multi-Armed Bandit Mechanisms for Multi-Slot Sponsored Search Auctions
In pay-per click sponsored search auctions which are cur- rently extensively used by search engines, the auction for a keyword involves a certain number of advertisers (say k) c...
Akash Das Sarma, Sujit Gujar, Y. Narahari
106
Voted
ALT
2007
Springer
16 years 19 days 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...
153
Voted
WIOPT
2011
IEEE
14 years 7 months ago
Network utility maximization over partially observable Markovian channels
Abstract—This paper considers maximizing throughput utility in a multi-user network with partially observable Markov ON/OFF channels. Instantaneous channel states are never known...
Chih-Ping Li, Michael J. Neely
139
Voted
COLT
2008
Springer
15 years 5 months ago
Adapting to a Changing Environment: the Brownian Restless Bandits
In the multi-armed bandit (MAB) problem there are k distributions associated with the rewards of playing each of k strategies (slot machine arms). The reward distributions are ini...
Aleksandrs Slivkins, Eli Upfal
125
Voted
SIGECOM
2009
ACM
83views ECommerce» more  SIGECOM 2009»
15 years 10 months ago
The price of truthfulness for pay-per-click auctions
We analyze the problem of designing a truthful pay-per-click auction where the click-through-rates (CTR) of the bidders are unknown to the auction. Such an auction faces the class...
Nikhil R. Devanur, Sham M. Kakade