46 search results - page 5 / 10 » colt 2008 |
93
Voted
COLT
2008
Springer
15 years 2 months ago
2008
Springer
We show how models for prediction with expert advice can be defined concisely and clearly using hidden Markov models (HMMs); standard HMM algorithms can then be used to efficientl...
100
click to vote
COLT
2008
Springer
15 years 2 months ago
2008
Springer
We design and analyze interacting online algorithms for multitask classification that perform better than independent learners whenever the tasks are related in a certain sense. W...
81
Voted
COLT
2008
Springer
15 years 2 months ago
2008
Springer
We present a modification of the algorithm of Dani et al. [8] for the online linear optimization problem in the bandit setting, which with high probability has regret at most O ( ...
131
click to vote
COLT
2010
Springer
14 years 10 months ago
2010
Springer
We describe online algorithms for learning a rotation from pairs of unit vectors in Rn . We show that the expected regret of our online algorithm compared to the best fixed rotati...
143
Voted
COLT
2001
Springer
15 years 5 months ago
2001
Springer
We prove strong noise-tolerance properties of a potential-based boosting algorithm, similar to MadaBoost (Domingo and Watanabe, 2000) and SmoothBoost (Servedio, 2003). Our analysi...