2376 search results - page 1 / 476 » More Efficient Internal-Regret-Minimizing Algorithms |
COLT
2008
Springer
13 years 6 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...
RECOMB
2008
Springer
14 years 5 months ago
2008
Springer
ISAAC
2007
Springer
13 years 11 months ago
2007
Springer
ICML
2007
IEEE
14 years 5 months ago
2007
IEEE
An efficient and general multiple kernel learning (MKL) algorithm has been recently proposed by Sonnenburg et al. (2006). This approach has opened new perspectives since it makes ...
PODS
2006
ACM
14 years 4 months ago
2006
ACM
In this paper, we give a simple scheme for identifying approximate frequent items over a sliding window of size n. Our scheme is deterministic and does not make any assumption on ...