Sciweavers

39 search results - page 8 / 8
» colt 2006
Sort
View
COLT
2006
Springer
15 years 3 months ago
Logarithmic Regret Algorithms for Online Convex Optimization
In an online convex optimization problem a decision-maker makes a sequence of decisions, i.e., chooses a sequence of points in Euclidean space, from a fixed feasible set. After ea...
Elad Hazan, Adam Kalai, Satyen Kale, Amit Agarwal
COLT
2008
Springer
15 years 1 months ago
An Information Theoretic Framework for Multi-view Learning
In the multi-view learning paradigm, the input variable is partitioned into two different views X1 and X2 and there is a target variable Y of interest. The underlying assumption i...
Karthik Sridharan, Sham M. Kakade
JCSS
2006
77views more  JCSS 2006»
14 years 12 months ago
Sequential predictions based on algorithmic complexity
This paper studies sequence prediction based on the monotone Kolmogorov complexity Km=-log m, i.e. based on universal deterministic/one-part MDL. m is extremely close to Solomonof...
Marcus Hutter
ICML
2006
IEEE
16 years 21 days ago
Totally corrective boosting algorithms that maximize the margin
We consider boosting algorithms that maintain a distribution over a set of examples. At each iteration a weak hypothesis is received and the distribution is updated. We motivate t...
Gunnar Rätsch, Jun Liao, Manfred K. Warmuth