A PAC-Bayesian Perspective on Structured ...
Type de document :
Pré-publication ou Document de travail
Titre :
A PAC-Bayesian Perspective on Structured Prediction with Implicit Loss Embeddings
Auteur(s) :
Cantelobre, Théophile [Auteur]
Mines Paris - PSL (École nationale supérieure des mines de Paris)
MOdel for Data Analysis and Learning [MODAL]
The Inria London Programme [Inria-London]
Guedj, Benjamin [Auteur]
University College of London [London] [UCL]
Department of Computer science [University College of London] [UCL-CS]
Inria-CWI [Inria-CWI]
MOdel for Data Analysis and Learning [MODAL]
The Inria London Programme [Inria-London]
Pérez-Ortiz, María [Auteur]
University College of London [London] [UCL]
Department of Computer science [University College of London] [UCL-CS]
The Inria London Programme [Inria-London]
Shawe-Taylor, John [Auteur]
University College of London [London] [UCL]
Department of Computer science [University College of London] [UCL-CS]
The Inria London Programme [Inria-London]
Mines Paris - PSL (École nationale supérieure des mines de Paris)
MOdel for Data Analysis and Learning [MODAL]
The Inria London Programme [Inria-London]
Guedj, Benjamin [Auteur]
University College of London [London] [UCL]
Department of Computer science [University College of London] [UCL-CS]
Inria-CWI [Inria-CWI]
MOdel for Data Analysis and Learning [MODAL]
The Inria London Programme [Inria-London]
Pérez-Ortiz, María [Auteur]
University College of London [London] [UCL]
Department of Computer science [University College of London] [UCL-CS]
The Inria London Programme [Inria-London]
Shawe-Taylor, John [Auteur]
University College of London [London] [UCL]
Department of Computer science [University College of London] [UCL-CS]
The Inria London Programme [Inria-London]
Mot(s)-clé(s) en anglais :
Statistical learning theory
PAC-Bayes theory
Structured output prediction
Implicit Loss Embeddings
Generalization bounds
PAC-Bayes theory
Structured output prediction
Implicit Loss Embeddings
Generalization bounds
Discipline(s) HAL :
Informatique [cs]/Apprentissage [cs.LG]
Statistiques [stat]/Machine Learning [stat.ML]
Statistiques [stat]/Théorie [stat.TH]
Statistiques [stat]/Machine Learning [stat.ML]
Statistiques [stat]/Théorie [stat.TH]
Résumé en anglais : [en]
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 ...
Lire la suite >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.Lire moins >
Lire la suite >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.Lire moins >
Langue :
Anglais
Commentaire :
38 pages
Collections :
Source :
Fichiers
- document
- Accès libre
- Accéder au document
- 2012.03780.pdf
- Accès libre
- Accéder au document
- 2012.03780
- Accès libre
- Accéder au document