Sciweavers

66 search results - page 10 / 14
» The Nonstochastic Multiarmed Bandit Problem
Sort
View
ICML
2010
IEEE
13 years 8 months ago
Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design
Many applications require optimizing an unknown, noisy function that is expensive to evaluate. We formalize this task as a multiarmed bandit problem, where the payoff function is ...
Niranjan Srinivas, Andreas Krause, Sham Kakade, Ma...
TSP
2012
12 years 3 months ago
Sensing and Probing Cardinalities for Active Cognitive Radios
—In a cognitive radio network, opportunistic spectrum access (OSA) to the underutilized spectrum involves not only sensing the spectrum occupancy but also probing the channel qua...
Thang Van Nguyen, Hyundong Shin, Tony Q. S. Quek, ...
COLT
2008
Springer
13 years 9 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
SIGECOM
2009
ACM
83views ECommerce» more  SIGECOM 2009»
14 years 2 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
ICML
2001
IEEE
14 years 8 months ago
Expectation Maximization for Weakly Labeled Data
We call data weakly labeled if it has no exact label but rather a numerical indication of correctness of the label "guessed" by the learning algorithm - a situation comm...
Yuri A. Ivanov, Bruce Blumberg, Alex Pentland