COLT
2000
Springer
13 years 12 months ago
2000
Springer
This paper collects together a miscellany of results originally motivated by the analysis of the generalization performance of the “maximum-margin” algorithm due to Vapnik and...
COLT
2000
Springer
13 years 12 months ago
2000
Springer
The present paper deals with the averagecase complexity of various algorithms for learning univariate polynomials. For this purpose an appropriate framework is introduced. Based o...
COLT
2000
Springer
13 years 12 months ago
2000
Springer
We describe a novel family of PAC model algorithms for learning linear threshold functions. The new algorithms work by boosting a simple weak learner and exhibit complexity bounds...
COLT
2000
Springer
13 years 12 months ago
2000
Springer
Boosting algorithms like AdaBoost and Arc-GV are iterative strategies to minimize a constrained objective function, equivalent to Barrier algorithms. Based on this new understandi...
COLT
2000
Springer
13 years 12 months ago
2000
Springer
Good-Turing adjustments of word frequencies are an important tool in natural language modeling. In particular, for any sample of words, there is a set of words not occuring in tha...
COLT
2000
Springer
13 years 12 months ago
2000
Springer
COLT
2000
Springer
13 years 12 months ago
2000
Springer
Haussler, Kearns, Seung and Tishby introduced the notion of a shell decomposition of the union bound as a means of understanding certain empirical phenomena in learning curves suc...
COLT
2000
Springer
13 years 12 months ago
2000
Springer
We give the first rigorous upper bounds on the error of temporal difference (td) algorithms for policy evaluation as a function of the amount of experience. These upper bounds pr...
COLT
2000
Springer
13 years 12 months ago
2000
Springer
COLT
2000
Springer
13 years 12 months ago
2000
Springer
We combine the results of [13] and [8] and derive a continuous variant of a large class of drifting games. Our analysis furthers the understanding of the relationship between boos...