11910 search results - page 290 / 2382 » Online Learning Algorithms |
203
click to vote
ML
2007
ACM
15 years 6 months ago
2007
ACM
We offer a new formal criterion for agent-centric learning in multi-agent systems, that is, learning that maximizes one’s rewards in the presence of other agents who might also...
218
click to vote
SODA
2012
ACM
13 years 9 months ago
2012
ACM
Motivated by online ad allocation, we study the problem of simultaneous approximations for the adversarial and stochastic online budgeted allocation problem. This problem consists...
198
click to vote
ICMLC
2005
Springer
16 years 3 days ago
2005
Springer
Abstract. Many supervised and unsupervised learning algorithms depend on the choice of an appropriate distance metric. While metric learning for supervised learning tasks has a lon...
158
click to vote
WADS
2007
Springer
16 years 21 days ago
2007
Springer
The dynamic TCP acknowledgement problem formulated by Dooly et al. has been intensively studied in the area of competitive analysis. However, their framework does not consider the ...
148
click to vote
COLT
1993
Springer
15 years 10 months ago
1993
Springer
We introduce a new formal model in which a learning algorithm must combine a collection of potentially poor but statistically independent hypothesis functions in order to approxima...