Pré-Publication, Document De Travail Année : 2020

A PAC-Bayesian Perspective on Structured Prediction with Implicit Loss Embeddings

Résumé

Many practical machine learning tasks can be framed as Structured prediction problems, where several output variables are predicted and considered interdependent. Recent theoretical advances in structured prediction have focused on obtaining fast rates convergence guarantees, especially in the Implicit Loss Embedding (ILE) framework. PAC-Bayes has gained interest recently for its capacity of producing tight risk bounds for predictor distributions. This work proposes a novel PAC-Bayes perspective on the ILE Structured prediction framework. We present two generalization bounds, on the risk and excess risk, which yield insights into the behavior of ILE predictors. Two learning algorithms are derived from these bounds. The algorithms are implemented and their behavior analyzed, with source code available at https://github.com/theophilec/ PAC-Bayes-ILE-Structured-Prediction.

Fichier principal
Vignette du fichier
2012.03780.pdf (2.7 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-03046401 , version 1 (08-12-2020)

Licence

Identifiants

Citer

Théophile Cantelobre, Benjamin Guedj, María Pérez-Ortiz, John Shawe-Taylor. A PAC-Bayesian Perspective on Structured Prediction with Implicit Loss Embeddings. 2020. ⟨hal-03046401⟩
269 Consultations
418 Téléchargements

Altmetric

Partager

  • More