15 search results - page 1 / 3 » Improved Risk Tail Bounds for On-Line Algorithms |
TIT
2008
13 years 5 months ago
2008
We prove the strongest known bound for the risk of hypotheses selected from the ensemble generated by running a learning algorithm incrementally on the training data. Our result i...
NIPS
2001
13 years 7 months ago
2001
In this paper, it is shown how to extract a hypothesis with small risk from the ensemble of hypotheses generated by an arbitrary on-line learning algorithm run on an independent an...
COCOON
2006
Springer
13 years 9 months ago
2006
Springer
We study an on-line broadcast scheduling problem in which requests have deadlines, and the objective is to maximize the weighted throughput, i.e., the weighted total length of the ...
FOCS
1993
IEEE
13 years 9 months ago
1993
IEEE
We consider the following scenario. A point robot is placed at some start location ¡ in a 2dimensional scene containing oriented rectangular obstacles. The robot must repeatedly ...
MST
2002
13 years 5 months ago
2002
Abstract. In this paper we consider communication issues arising in cellular (mobile) networks that utilize frequency division multiplexing (FDM) technology. In such networks, many...