412 search results - page 18 / 83 » A New Proof of the F5 Algorithm |
146
click to vote
COLT
2004
Springer
15 years 9 months ago
2004
Springer
For hyper-rectangles in Rd Auer et al. [1] proved a PAC bound of O 1 (d + log 1 ) , where and are the accuracy and confidence parameters. It is still an open question whether one...
188
click to vote
SYNASC
2008
IEEE
16 years 8 days ago
2008
IEEE
Abstract. A new approach to the design of massively parallel and interactive programming languages has been recently proposed using rv-systems (interactive systems with registers a...
134
click to vote
LPAR
2010
Springer
15 years 3 months ago
2010
Springer
Unification in Description Logics has been proposed as a novel inference service that can, for example, be used to detect redundancies in ontologies. In a recent paper, we have sho...
136
click to vote
CSL
2010
Springer
15 years 7 months ago
2010
Springer
Abstract. Recent analysis of sequential algorithms resulted in their axiomatization and in a representation theorem stating that, for any sealgorithm, there is an abstract state ma...
162
click to vote
NIPS
2007
15 years 7 months ago
2007
We present four new reinforcement learning algorithms based on actor-critic and natural-gradient ideas, and provide their convergence proofs. Actor-critic reinforcement learning m...