COLT
2010
Springer
13 years 9 months ago
2010
Springer
In recent years analysis of complexity of learning Gaussian mixture models from sampled data has received significant attention in computational machine learning and theory commun...
COLT
2010
Springer
13 years 9 months ago
2010
Springer
We consider an online learning setting where at each time step the decision maker has to choose how to distribute the future loss between k alternatives, and then observes the los...
COLT
2010
Springer
13 years 9 months ago
2010
Springer
Bandit convex optimization is a special case of online convex optimization with partial information. In this setting, a player attempts to minimize a sequence of adversarially gen...
COLT
2010
Springer
13 years 9 months ago
2010
Springer
We investigate the problem of active learning on a given tree whose nodes are assigned binary labels in an adversarial way. Inspired by recent results by Guillory and Bilmes, we c...
COLT
2010
Springer
13 years 9 months ago
2010
Springer
We define a new model of quantum learning that we call Predictive Quantum (PQ). This is a quantum analogue of PAC, where during the testing phase the student is only required to a...
COLT
2010
Springer
13 years 9 months ago
2010
Springer
Let S be an arbitrary measurable space, T R and (X, Y ) be a random couple in S
COLT
2010
Springer
13 years 9 months ago
2010
Springer
COLT
2010
Springer
13 years 9 months ago
2010
Springer
Abstract. We pose the problem of determining the rate of convergence at which AdaBoost minimizes exponential loss. Boosting is the problem of combining many "weak," high-...
COLT
2010
Springer
13 years 9 months ago
2010
Springer
COLT
2010
Springer
13 years 9 months ago
2010
Springer
We study graph estimation and density estimation in high dimensions, using a family of density estimators based on forest structured undirected graphical models. For density estim...