2944 search results - page 386 / 589 » Improving Bound Propagation |
167
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...
139
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
STOC
2009
ACM
16 years 7 months ago
2009
ACM
We give explicit constructions of epsilon nets for linear threshold functions on the binary cube and on the unit sphere. The size of the constructed nets is polynomial in the dime...
159
click to vote
DCC
2009
IEEE
16 years 7 months ago
2009
IEEE
This paper considers the problem of transmitting the difference of two positively correlated Gaussian sources over a two-user additive Gaussian noise multiple access channel (MAC)...
154
click to vote
STOC
2003
ACM
16 years 6 months ago
2003
ACM
We study novel combinatorial properties of graphs that allow us to devise a completely new approach to dynamic all pairs shortest paths problems. Our approach yields a fully dynam...