3991 search results - page 523 / 799 » Bounding homogeneous models |
175
click to vote
ICML
2006
IEEE
16 years 7 months ago
2006
IEEE
For a Markov Decision Process with finite state (size S) and action spaces (size A per state), we propose a new algorithm--Delayed Q-Learning. We prove it is PAC, achieving near o...
144
click to vote
ICML
2003
IEEE
16 years 7 months ago
2003
IEEE
Recent theoretical results have shown that improved bounds on generalization error of classifiers can be obtained by explicitly taking the observed margin distribution of the trai...
153
click to vote
ICML
2003
IEEE
16 years 7 months ago
2003
IEEE
We present a new type of multi-class learning algorithm called a linear-max algorithm. Linearmax algorithms learn with a special type of attribute called a sub-expert. A sub-exper...
222
click to vote
VLSID
2004
IEEE
16 years 7 months ago
2004
IEEE
This paper presents a novel technique for abstracting designs in order to increase the efficiency of formal property checking. Bounded Model Checking (BMC), using Satisfiability (...
164
click to vote
SODA
2010
ACM
16 years 4 months ago
2010
ACM
We consider the complexity of sorting strings in the model that counts comparisons between symbols and not just comparisons between strings. We show that for any set of strings S ...