Home > Research > Publications & Outputs > FIESTA

Electronic data

  • 1906.12230v1

    Accepted author manuscript, 388 KB, PDF document

Links

View graph of relations

FIESTA: Fast IdEntification of State-of-The-Art models using adaptive bandit algorithms

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paper

Published
Publication date30/07/2019
Host publicationProceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Place of PublicationStroudsburg PA
PublisherAssociation for Computational Linguistics
Pages2920-2930
Number of pages11
Original languageEnglish

Abstract

We present FIESTA, a model selection approach that significantly reduces the computational resources required to reliably identify state-of-the-art performance from large collections of candidate models. Despite being known to produce unreliable comparisons, it is still common practice to compare model evaluations based on single choices of random seeds. We show that reliable model selection also requires evaluations based on multiple train-test splits (contrary to common practice in many shared tasks). Using bandit theory from the statistics literature, we are able to adaptively determine appropriate numbers of data splits and random seeds used to evaluate each model, focusing computational resources on the evaluation of promising models whilst avoiding wasting evaluations on models with lower performance. Furthermore, our user-friendly Python implementation produces confidence guarantees of correctly selecting the optimal model. We evaluate our algorithms by selecting between 8 target-dependent sentiment analysis methods using dramatically fewer model evaluations than current model selection approaches.