Sciweavers

COLT
2007
Springer
13 years 10 months ago
Margin Based Active Learning
We present a framework for margin based active learning of linear separators. We instantiate it for a few important cases, some of which have been previously considered in the lite...
Maria-Florina Balcan, Andrei Z. Broder, Tong Zhang
COLT
2007
Springer
13 years 10 months ago
Improved Rates for the Stochastic Continuum-Armed Bandit Problem
Abstract. Considering one-dimensional continuum-armed bandit problems, we propose an improvement of an algorithm of Kleinberg and a new set of conditions which give rise to improve...
Peter Auer, Ronald Ortner, Csaba Szepesvári
COLT
2007
Springer
13 years 10 months ago
Multitask Learning with Expert Advice
Jacob Abernethy, Peter L. Bartlett, Alexander Rakh...
COLT
2007
Springer
13 years 10 months ago
Rademacher Margin Complexity
Liwei Wang, Jufu Feng
COLT
2007
Springer
13 years 10 months ago
Strategies for Prediction Under Imperfect Monitoring
Abstract. We propose simple randomized strategies for sequential prediction under imperfect monitoring, that is, when the forecaster does not have access to the past outcomes but r...
Gábor Lugosi, Shie Mannor, Gilles Stoltz
COLT
2007
Springer
13 years 10 months ago
Stability of k -Means Clustering
Shai Ben-David, Dávid Pál, Hans-Ulri...
COLT
2007
Springer
13 years 10 months ago
Observational Learning in Random Networks
In the standard model of observational learning, n agents sequentially decide between two alternatives a or b, one of which is objectively superior. Their choice is based on a stoc...
Julian Lorenz, Martin Marciniszyn, Angelika Steger
COLT
2007
Springer
13 years 10 months ago
A Lower Bound for Agnostically Learning Disjunctions
We prove that the concept class of disjunctions cannot be pointwise approximated by linear combinations of any small set of arbitrary real-valued functions. That is, suppose there ...
Adam R. Klivans, Alexander A. Sherstov
COLT
2007
Springer
13 years 10 months ago
How Good Is a Kernel When Used as a Similarity Measure?
Recently, Balcan and Blum [1] suggested a theory of learning based on general similarity functions, instead of positive semi-definite kernels. We study the gap between the learnin...
Nathan Srebro