COLT
2006
Springer
14 years 3 months ago
2006
Springer
In this paper, we study a sequential decision making problem. The objective is to maximize the total reward while satisfying constraints, which are defined at every time step. The...
COLT
2006
Springer
14 years 3 months ago
2006
Springer
We consider online learning in repeated decision problems, within the framework of a repeated game against an arbitrary opponent. For repeated matrix games, well known results esta...
COLT
2006
Springer
14 years 3 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...
COLT
2006
Springer
14 years 3 months ago
2006
Springer
Abstract. We present an improved version of random projections that takes advantage of marginal norms. Using a maximum likelihood estimator (MLE), marginconstrained random projecti...
COLT
2006
Springer
14 years 3 months ago
2006
Springer
We study the average number of well-chosen labeled examples that are required for a helpful teacher to uniquely specify a target function within a concept class. This "average...
COLT
2006
Springer
14 years 3 months ago
2006
Springer
We consider the problem of optimality, in a minimax sense, and adaptivity to the margin and to regularity in binary classification. We prove an oracle inequality, under the margin ...
COLT
2006
Springer
14 years 3 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...
COLT
2006
Springer
14 years 3 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...
COLT
2006
Springer
14 years 3 months ago
2006
Springer
We study the problem of online learning of multiple tasks in parallel. On each online round, the algorithm receives an instance and makes a prediction for each one of the parallel ...
COLT
2006
Springer
14 years 3 months ago
2006
Springer
We describe a new approach for understanding the difficulty of designing efficient learning algorithms. We prove that the existence of an efficient learning algorithm for a circui...