Sciweavers

Share
COLT
2004
Springer
9 years 3 months ago
The Budgeted Multi-armed Bandit Problem
straction of the following scenarios: choosing from among a set of alternative treatments after a fixed number of clinical trials, determining the best parameter settings for a pro...
Omid Madani, Daniel J. Lizotte, Russell Greiner
COLT
2004
Springer
9 years 3 months ago
Suboptimal Behavior of Bayes and MDL in Classification Under Misspecification
We show that forms of Bayesian and MDL inference that are often applied to classification problems can be inconsistent. This means that there exists a learning problem such that fo...
Peter Grünwald, John Langford
COLT
2004
Springer
9 years 3 months ago
Model Selection by Bootstrap Penalization for Classification
We consider the binary classification problem. Given an i.i.d. sample drawn from the distribution of an X
Magalie Fromont
COLT
2004
Springer
9 years 3 months ago
Minimizing Regret with Label Efficient Prediction
We investigate label efficient prediction, a variant, proposed by Helmbold and Panizza, of the problem of prediction with expert advice. In this variant, the forecaster, after gues...
Nicolò Cesa-Bianchi, Gábor Lugosi, G...
COLT
2004
Springer
9 years 3 months ago
Regret Bounds for Hierarchical Classification with Linear-Threshold Functions
We study the problem of classifying data in a given taxonomy when classifications associated with multiple and/or partial paths are allowed. We introduce an incremental algorithm u...
Nicolò Cesa-Bianchi, Alex Conconi, Claudio ...
COLT
2004
Springer
9 years 3 months ago
Oracle Bounds and Exact Algorithm for Dyadic Classification Trees
This paper introduces a new method using dyadic decision trees for estimating a classification or a regression function in a multiclass classification problem. The estimator is bas...
Gilles Blanchard, Christin Schäfer, Yves Roze...
COLT
2004
Springer
9 years 3 months ago
A New PAC Bound for Intersection-Closed Concept Classes
For hyper-rectangles in Rd Auer et al. [1] proved a PAC bound of O 1 (d + log 1 ) , where and are the accuracy and confidence parameters. It is still an open question whether one...
Peter Auer, Ronald Ortner
COLT
2004
Springer
9 years 4 months ago
Statistical Properties of Kernel Principal Component Analysis
The main goal of this paper is to prove inequalities on the reconstruction error for Kernel Principal Component Analysis. With respect to previous work on this topic, our contribu...
Laurent Zwald, Olivier Bousquet, Gilles Blanchard
COLT
2004
Springer
9 years 4 months ago
The Optimal PAC Algorithm
Manfred K. Warmuth
books