Inductive learning is based on inferring a general rule from a finite data set and using it to label new data. In transduction one attempts to solve the problem of using a labeled training set to label a set of unlabeled points, which are given to the learner prior to learning. Although transduction seems at the outset to be an easier task than induction, there have not been many provably useful algorithms for transduction. Moreover, the precise relation between induction and transduction has not yet been determined. The main theoretical developments related to transduction were presented by Vapnik more than twenty years ago. One of Vapnik's basic results is a rather tight error bound for transduction based on exact computation...
The exchange of ideas between computer science and statistical physics has advanced the understandin...
In this paper we introduce and investigate a mathematically rigorous theory of learning curves that ...
For large, real-world inductive learning problems, the number of training examples often must be lim...
Inductive learning is based on inferring a general rule from a finite data set and using it to labe...
Inductive learning is based on inferring a general rule from a finite data set and using it to label...
This paper is concerned with transductive learning. Although transduction appears to be an easier ta...
All authors contributed equally to this work. We propose a PAC-Bayesian analysis of the transductive...
Abstract. Approximating adequate number of clusters in multidimen-sional data is an open area of res...
At its strongest, Hume's problem of induction denies the existence of any well justified assumptionl...
International audienceWe show two novel concentration inequalities for suprema of empirical processe...
Part 4: First Conformal Prediction and Its Applications Workshop (COPA 2012)International audienceGi...
Traditional supervised approaches realize an inductive learning process: A model is learnt from labe...
We show two novel concentration inequalities for suprema of empirical processes when sampling withou...
AbstractThe analysis of theoretical learning models is basically concerned with the comparison of id...
Many of the central problems of cognitive science are problems of induction, calling for uncertain i...
The exchange of ideas between computer science and statistical physics has advanced the understandin...
In this paper we introduce and investigate a mathematically rigorous theory of learning curves that ...
For large, real-world inductive learning problems, the number of training examples often must be lim...
Inductive learning is based on inferring a general rule from a finite data set and using it to labe...
Inductive learning is based on inferring a general rule from a finite data set and using it to label...
This paper is concerned with transductive learning. Although transduction appears to be an easier ta...
All authors contributed equally to this work. We propose a PAC-Bayesian analysis of the transductive...
Abstract. Approximating adequate number of clusters in multidimen-sional data is an open area of res...
At its strongest, Hume's problem of induction denies the existence of any well justified assumptionl...
International audienceWe show two novel concentration inequalities for suprema of empirical processe...
Part 4: First Conformal Prediction and Its Applications Workshop (COPA 2012)International audienceGi...
Traditional supervised approaches realize an inductive learning process: A model is learnt from labe...
We show two novel concentration inequalities for suprema of empirical processes when sampling withou...
AbstractThe analysis of theoretical learning models is basically concerned with the comparison of id...
Many of the central problems of cognitive science are problems of induction, calling for uncertain i...
The exchange of ideas between computer science and statistical physics has advanced the understandin...
In this paper we introduce and investigate a mathematically rigorous theory of learning curves that ...
For large, real-world inductive learning problems, the number of training examples often must be lim...