Programming by Feedback

Riad Akrour 1, 2 Marc Schoenauer 1, 2 Michèle Sebag 1 Jean-Christophe Souplet 1
2 TAO - Machine Learning and Optimisation
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
Abstract : This paper advocates a new ML-based programming framework, called Programming by Feedback (PF), which involves a sequence of interactions between the active computer and the user. The latter only provides preference judgments on pairs of solutions supplied by the active computer. The active computer involves one learning and one optimization components; the learning component estimates the user's utility function and accounts for the user's (possibly limited) competence; the optimization component explores the search space and returns the most appropriate candidate solution. A proof of principle of the approach is proposed, showing that PF requires a handful of interactions in order to solve some discrete and continuous benchmark problems.
Complete list of metadatas

Cited literature [28 references]  Display  Hide  Download

https://hal.inria.fr/hal-00980839
Contributor : Riad Akrour <>
Submitted on : Tuesday, April 22, 2014 - 10:48:41 AM
Last modification on : Thursday, April 5, 2018 - 12:30:12 PM
Long-term archiving on : Monday, April 10, 2017 - 3:51:24 PM

File

programming_by_feedback.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00980839, version 1

Collections

Citation

Riad Akrour, Marc Schoenauer, Michèle Sebag, Jean-Christophe Souplet. Programming by Feedback. International Conference on Machine Learning, Jun 2014, Pékin, China. pp.1503-1511. ⟨hal-00980839⟩

Share

Metrics

Record views

1568

Files downloads

593