122
click to vote
COLT
15 years 6 months ago
2006 Springer 
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...
123
click to vote
COLT
15 years 6 months ago
2006 Springer 
Abstract. The regularization functional induced by the graph Laplacian of a random neighborhood graph based on the data is adaptive in two ways. First it adapts to an underlying ma...
93
Voted
COLT
15 years 6 months ago
2006 Springer 
Bounds are given for the empirical and expected Rademacher complexity of classes of linear transformations from a Hilbert space H to a ...nite dimensional space. The results imply ...
112
Voted
COLT
15 years 6 months ago
2006 Springer 
Generative algorithms for learning classifiers use training data to separately estimate a probability model for each class. New items are classified by comparing their probabiliti...
|
Machine Learning