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

Meta-learning from Learning Curves Challenge: Lessons learned from the First Round and Design of the Second Round

Manh Hung Nguyen 1, * Lisheng Sun 1 Nathan Grinsztajn 2, 3 Isabelle Guyon 4, 1, 5 
* Corresponding author
3 Scool - Scool
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
5 TAU - TAckling the Underspecified
Inria Saclay - Ile de France, LISN - Laboratoire Interdisciplinaire des Sciences du Numérique
Abstract : Meta-learning from learning curves is an important yet often neglected research area in the Machine Learning community. We introduce a series of Reinforcement Learning-based meta-learning challenges, in which an agent searches for the best suited algorithm for a given dataset, based on feedback of learning curves from the environment. The first round attracted participants both from academia and industry. This paper analyzes the results of the first round (accepted to the competition program of WCCI 2022), to draw insights into what makes a meta-learner successful at learning from learning curves. With the lessons learned from the first round and the feedback from the participants, we have designed the second round of our challenge with a new protocol and a new meta-dataset. The second round of our challenge is accepted at the AutoML-Conf 2022 and currently ongoing .
Document type :
Preprints, Working Papers, ...
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03725313
Contributor : Manh Hung Nguyen Connect in order to contact the contributor
Submitted on : Wednesday, August 3, 2022 - 9:44:24 AM
Last modification on : Wednesday, September 7, 2022 - 8:14:05 AM

Files

main.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03725313, version 1
  • ARXIV : 2208.02821

Citation

Manh Hung Nguyen, Lisheng Sun, Nathan Grinsztajn, Isabelle Guyon. Meta-learning from Learning Curves Challenge: Lessons learned from the First Round and Design of the Second Round. 2022. ⟨hal-03725313⟩

Share

Metrics

Record views

16

Files downloads

6