Skip to Main content Skip to Navigation
Book sections

AutoML @ NeurIPS 2018 challenge: Design and Results

Hugo Escalante 1, 2 Wei-Wei Tu 3 Isabelle Guyon 2, 4 Daniel Silver 5, 6 Evelyne Viegas 6 Yuqiang Chen 3 Wenyuan Dai 3 Qiang Yang 7
1 INAOE - Instituto Nacional de Astrofísica, Óptica y Electrónica
2 Chalearn
3 4Paradigm
4 TAU - TAckling the Underspecified
Inria Saclay - Ile de France, LRI - Laboratoire de Recherche en Informatique
5 Acadia University
6 Microsoft Research [Redmond]
7 HKUST - Hong Kong University of Science and Technology
Abstract : We organized a competition on Autonomous Lifelong Machine Learning with Drift that was part of the competition program of NeurIPS 2018. This data driven competition asked participants to develop computer programs capable of solving supervised learning problems where the i.i.d. assumption did not hold. Large data sets were arranged in a lifelong learning and evaluation scenario and CodaLab was used as the challenge platform. The challenge attracted more than 300 participants in its two month duration. This chapter describes the design of the challenge and summarizes its main results.
Keywords : Automatic machine learning Concept drift Life long learning Challenge organization
Document type :
Book sections
Complete list of metadata
https://hal.inria.fr/hal-03159764
Contributor : Marc Schoenauer <>
Submitted on : Thursday, March 4, 2021 - 4:48:58 PM
Last modification on : Wednesday, April 14, 2021 - 3:40:04 AM

File

Vignette du document
1903.05263.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03159764, version 1

Collections

UMR8623 | CNRS | CENTRALESUPELEC | INRIA | LISN | LRI-AO | LISN-AO | GS-ENGINEERING

Citation

Hugo Escalante, Wei-Wei Tu, Isabelle Guyon, Daniel Silver, Evelyne Viegas, et al.. AutoML @ NeurIPS 2018 challenge: Design and Results. Escalera, Sergio and Herbrich, Ralf. The NeurIPS '18 Competition, Springer Verlag, pp.209--229, 2020, 978-3-030-29135-8. ⟨hal-03159764⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

47

Files downloads

371

 

Contact                    Legal Notice                    Personal Data