Sciweavers

Share
COLT
2005
Springer
8 years 10 months ago
Data Dependent Concentration Bounds for Sequential Prediction Algorithms
Abstract. We investigate the generalization behavior of sequential prediction (online) algorithms, when data are generated from a probability distribution. Using some newly develop...
Tong Zhang
COLT
2005
Springer
8 years 10 months ago
Loss Bounds for Online Category Ranking
Category ranking is the task of ordering labels with respect to their relevance to an input instance. In this paper we describe and analyze several algorithms for online category r...
Koby Crammer, Yoram Singer
COLT
2005
Springer
8 years 10 months ago
From External to Internal Regret
External regret compares the performance of an online algorithm, selecting among N actions, to the performance of the best of those actions in hindsight. Internal regret compares ...
Avrim Blum, Yishay Mansour
COLT
2005
Springer
9 years 1 months ago
Tracking the Best of Many Experts
András György, Tamás Linder, G&...
COLT
2005
Springer
9 years 1 months ago
Permutation Tests for Classification
Polina Golland, Feng Liang, Sayan Mukherjee, Dmitr...
COLT
2005
Springer
9 years 1 months ago
Ranking and Scoring Using Empirical Risk Minimization
A general model is proposed for studying ranking problems. We investigate learning methods based on empirical minimization of the natural estimates of the ranking risk. The empiric...
Stéphan Clémençon, Gáb...
COLT
2005
Springer
9 years 1 months ago
Localized Upper and Lower Bounds for Some Estimation Problems
Abstract. We derive upper and lower bounds for some statistical estimation problems. The upper bounds are established for the Gibbs algorithm. The lower bounds, applicable for all ...
Tong Zhang
COLT
2005
Springer
9 years 1 months ago
Leaving the Span
We discuss a simple sparse linear problem that is hard to learn with any algorithm that uses a linear combination of the training instances as its weight vector. The hardness holds...
Manfred K. Warmuth, S. V. N. Vishwanathan
COLT
2005
Springer
9 years 1 months ago
Rank, Trace-Norm and Max-Norm
We study the rank, trace-norm and max-norm as complexity measures of matrices, focusing on the problem of fitting a matrix with matrices having low complexity. We present generali...
Nathan Srebro, Adi Shraibman
COLT
2005
Springer
9 years 1 months ago
A New Perspective on an Old Perceptron Algorithm
Abstract. We present a generalization of the Perceptron algorithm. The new algorithm performs a Perceptron-style update whenever the margin of an example is smaller than a predefi...
Shai Shalev-Shwartz, Yoram Singer
books