COLT
2008
Springer
13 years 6 months ago
2008
Springer
Coordinate gradient learning is motivated by the problem of variable selection and determining variable covariation. In this paper we propose a novel unifying framework for coordi...
COLT
2008
Springer
13 years 6 months ago
2008
Springer
Prediction from expert advice is a fundamental problem in machine learning. A major pillar of the field is the existence of learning algorithms whose average loss approaches that ...
COLT
2008
Springer
13 years 6 months ago
2008
Springer
In the multi-armed bandit (MAB) problem there are k distributions associated with the rewards of playing each of k strategies (slot machine arms). The reward distributions are ini...
COLT
2008
Springer
13 years 6 months ago
2008
Springer
We study on-line decision problems where the set of actions that are available to the decision algorithm vary over time. With a few notable exceptions, such problems remained larg...
COLT
2008
Springer
13 years 6 months ago
2008
Springer
A Hilbert space embedding for probability measures has recently been proposed, with applications including dimensionality reduction, homogeneity testing and independence testing. ...
COLT
2008
Springer
13 years 6 months ago
2008
Springer
In recent work, Kalai, Klivans, Mansour, and Servedio [KKMS05] studied a variant of the "Low-Degree (Fourier) Algorithm" for learning under the uniform probability distr...
COLT
2008
Springer
13 years 6 months ago
2008
Springer
We study the problem of clustering discrete probability distributions with respect to the Kullback-Leibler (KL) divergence. This problem arises naturally in many applications. Our...
COLT
2008
Springer
13 years 6 months ago
2008
Springer
We study the properties of the agnostic learning framework of Haussler [Hau92] and Kearns, Schapire and Sellie [KSS94]. In particular, we address the question: is there any situat...
COLT
2008
Springer
13 years 6 months ago
2008
Springer
A pseudo-Boolean function is a real-valued function defined on {0, 1}n . A k-bounded function is a pseudo-Boolean function that can be expressed as a sum of subfunctions each of w...
COLT
2008
Springer
13 years 6 months ago
2008
Springer
We show how models for prediction with expert advice can be defined concisely and clearly using hidden Markov models (HMMs); standard HMM algorithms can then be used to efficientl...