3415 search results - page 252 / 683 » Lower bounds on kernelization |
168
click to vote
COLT
2008
Springer
15 years 8 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...
166
click to vote
EWRL
2008
15 years 8 months ago
2008
We consider planning in a Markovian decision problem, i.e., the problem of finding a good policy given access to a generative model of the environment. We propose to use fitted Q-i...
194
click to vote
NIPS
2008
15 years 8 months ago
2008
In this paper we consider approximate policy-iteration-based reinforcement learning algorithms. In order to implement a flexible function approximation scheme we propose the use o...
191
click to vote
PRL
2008
15 years 6 months ago
2008
We develop a new multiclass classification method that reduces the multiclass problem to a single binary classifier (SBC). Our method constructs the binary problem by embedding sm...
178
click to vote
DCC
2007
IEEE
16 years 6 months ago
2007
IEEE
We find lower bounds on the minimum distance and characterize codewords of small weight in low-density parity check codes defined by (dual) classical generalized quadrangles. We a...