83 search results - page 6 / 17 » Online Learning: Beyond Regret |
120
Voted
COLT
2008
Springer
15 years 3 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...
127
Voted
ICML
2010
IEEE
14 years 12 months ago
2010
IEEE
Online learning algorithms have recently risen to prominence due to their strong theoretical guarantees and an increasing number of practical applications for large-scale data ana...
100
click to vote
ICML
2009
IEEE
16 years 2 months ago
2009
IEEE
The kernel Perceptron is an appealing online learning algorithm that has a drawback: whenever it makes an error it must increase its support set, which slows training and testing ...
108
click to vote
COLT
2008
Springer
15 years 3 months ago
2008
Springer
We introduce an efficient algorithm for the problem of online linear optimization in the bandit setting which achieves the optimal O ( T) regret. The setting is a natural general...
145
Voted
CORR
2010
Springer
14 years 8 months ago
2010
Springer
We consider an opportunistic spectrum access (OSA) problem where the time-varying condition of each channel (e.g., as a result of random fading or certain primary users' activ...