Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

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

Théophile Cantelobre 1, 2 Benjamin Guedj 3, 4, 5, 2 María Pérez-Ortiz 3, 4 John Shawe-Taylor 3, 4
2 MODAL - MOdel for Data Analysis and Learning
Inria Lille - Nord Europe, LPP - Laboratoire Paul Painlevé - UMR 8524, METRICS - Evaluation des technologies de santé et des pratiques médicales - ULR 2694, Polytech Lille - École polytechnique universitaire de Lille, Université de Lille, Sciences et Technologies
Abstract : 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 PAC-Bayes-ILE-Structured-Prediction.
Complete list of metadatas
Contributor : Benjamin Guedj <>
Submitted on : Tuesday, December 8, 2020 - 1:44:34 PM
Last modification on : Thursday, December 10, 2020 - 3:06:43 AM


Files produced by the author(s)


  • HAL Id : hal-03046401, version 1
  • ARXIV : 2012.03780


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



Record views


Files downloads