COLT
2010
Springer
13 years 3 months ago
2010
Springer
We present a new method for regularized convex optimization and analyze it under both online and stochastic optimization settings. In addition to unifying previously known firstor...
COLT
2010
Springer
13 years 3 months ago
2010
Springer
We explore the relationship between a natural notion of unsupervised learning studied by Kearns et al. (STOC '94), which we call here "learning to create" (LTC), an...
COLT
2010
Springer
13 years 3 months ago
2010
Springer
In 1994, Y. Mansour conjectured that for every DNF formula on n variables with t terms there exists a polynomial p with tO(log(1/)) non-zero coefficients such that Ex{0,1}n [(p(x)...
COLT
2010
Springer
13 years 3 months ago
2010
Springer
COLT
2010
Springer
13 years 3 months ago
2010
Springer
We consider the problem of finding the best arm in a stochastic multi-armed bandit game. The regret of a forecaster is here defined by the gap between the mean reward of the optim...
COLT
2010
Springer
13 years 3 months ago
2010
Springer
We develop an online algorithm called Component Hedge for learning structured concept classes when the loss of a structured concept sums over its components. Example classes inclu...
COLT
2010
Springer
13 years 3 months ago
2010
Springer
We consider the dimensionality-reduction problem (finding a subspace approximation of observed data) for contaminated data in the high dimensional regime, where the number of obse...
COLT
2010
Springer
13 years 3 months ago
2010
Springer
Clustering is a central unsupervised learning task with a wide variety of applications. Not surprisingly, there exist many clustering algorithms. However, unlike classification ta...
COLT
2010
Springer
13 years 3 months ago
2010
Springer
COLT
2010
Springer
13 years 3 months ago
2010
Springer
We describe online algorithms for learning a rotation from pairs of unit vectors in Rn . We show that the expected regret of our online algorithm compared to the best fixed rotati...