PAC-Bayesian Theory for Transductive Learning

Luc Bégin, Pascal Germain, François Laviolette, Jean-Francis Roy
Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, PMLR 33:105-113, 2014.

Abstract

We propose a PAC-Bayesian analysis of the transductive learning setting, introduced by Vapnik [2008], by proposing a family of new bounds on the generalization error. Some of them are derived from their counterpart in the inductive setting, and others are new. We also compare their behavior.

Cite this Paper


BibTeX
@InProceedings{pmlr-v33-begin14, title = {{PAC-Bayesian Theory for Transductive Learning}}, author = {Luc Bégin and Pascal Germain and François Laviolette and Jean-Francis Roy}, booktitle = {Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics}, pages = {105--113}, year = {2014}, editor = {Samuel Kaski and Jukka Corander}, volume = {33}, series = {Proceedings of Machine Learning Research}, address = {Reykjavik, Iceland}, month = {22--25 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v33/begin14.pdf}, url = {http://proceedings.mlr.press/v33/begin14.html}, abstract = {We propose a PAC-Bayesian analysis of the transductive learning setting, introduced by Vapnik [2008], by proposing a family of new bounds on the generalization error. Some of them are derived from their counterpart in the inductive setting, and others are new. We also compare their behavior.} }
Endnote
%0 Conference Paper %T PAC-Bayesian Theory for Transductive Learning %A Luc Bégin %A Pascal Germain %A François Laviolette %A Jean-Francis Roy %B Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2014 %E Samuel Kaski %E Jukka Corander %F pmlr-v33-begin14 %I PMLR %P 105--113 %U http://proceedings.mlr.press/v33/begin14.html %V 33 %X We propose a PAC-Bayesian analysis of the transductive learning setting, introduced by Vapnik [2008], by proposing a family of new bounds on the generalization error. Some of them are derived from their counterpart in the inductive setting, and others are new. We also compare their behavior.
RIS
TY - CPAPER TI - PAC-Bayesian Theory for Transductive Learning AU - Luc Bégin AU - Pascal Germain AU - François Laviolette AU - Jean-Francis Roy BT - Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics DA - 2014/04/02 ED - Samuel Kaski ED - Jukka Corander ID - pmlr-v33-begin14 PB - PMLR DP - Proceedings of Machine Learning Research VL - 33 SP - 105 EP - 113 L1 - http://proceedings.mlr.press/v33/begin14.pdf UR - http://proceedings.mlr.press/v33/begin14.html AB - We propose a PAC-Bayesian analysis of the transductive learning setting, introduced by Vapnik [2008], by proposing a family of new bounds on the generalization error. Some of them are derived from their counterpart in the inductive setting, and others are new. We also compare their behavior. ER -
APA
Bégin, L., Germain, P., Laviolette, F. & Roy, J.. (2014). PAC-Bayesian Theory for Transductive Learning. Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 33:105-113 Available from http://proceedings.mlr.press/v33/begin14.html.

Related Material