3050 search results - page 115 / 610 » On-line Algorithms in Machine Learning |
111
Voted
COLT
2000
Springer
15 years 8 months ago
2000
Springer
We model reinforcement learning as the problem of learning to control a Partially Observable Markov Decision Process ( ¢¡¤£¦¥§ ), and focus on gradient ascent approache...
129
Voted
ML
2000
ACM
15 years 3 months ago
2000
ACM
This work focuses on algorithms which learn from examples to perform multiclass text and speech categorization tasks. Our approach is based on a new and improved family of boosting...
116
Voted
ICML
2006
IEEE
16 years 4 months ago
2006
IEEE
We show that it is possible to use data compression on independently obtained hypotheses from various tasks to algorithmically provide guarantees that the tasks are sufficiently r...
137
Voted
COLT
2008
Springer
15 years 5 months ago
2008
Springer
Standard no-internal-regret (NIR) algorithms compute a fixed point of a matrix, and hence typically require O(n3 ) run time per round of learning, where n is the dimensionality of...
178
click to vote
COLT
2001
Springer
15 years 8 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...