Cantelobre, Théophile;
Guedj, Benjamin;
Pérez-Ortiz, María;
Shawe-Taylor, John;
(2020)
A PAC-Bayesian Perspective on Structured Prediction with Implicit Loss Embeddings.
ArXiv
Preview |
Text
2012.03780v2.pdf - Other Download (2MB) | Preview |
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 https://github.com/theophilec/PAC-Bayes-ILE-Structured-Prediction.
| Type: | Working / discussion paper |
|---|---|
| Title: | A PAC-Bayesian Perspective on Structured Prediction with Implicit Loss Embeddings |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://doi.org/10.48550/arXiv.2012.03780 |
| Language: | English |
| Additional information: | This paper is published under the Creative Commons Attribution 4.0 International (CC-BY 4.0) license. |
| Keywords: | Statistical learning theory, PAC-Bayes theory, Structured output prediction, Implicit Loss Embeddings, Generalization bounds |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10160362 |
Archive Staff Only
 |
View Item |
