Celo: Training Versatile Learned Optimizers on a Compute Diet

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Moudgil, Abhinav, Knyazev, Boris, Lajoie, Guillaume, Belilovsky, Eugene
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908414308777984
author Moudgil, Abhinav
Knyazev, Boris
Lajoie, Guillaume
Belilovsky, Eugene
author_facet Moudgil, Abhinav
Knyazev, Boris
Lajoie, Guillaume
Belilovsky, Eugene
contents Learned optimization has emerged as a promising alternative to hand-crafted optimizers, with the potential to discover stronger learned update rules that enable faster, hyperparameter-free training of neural networks. A critical element for practically useful learned optimizers, that can be used off-the-shelf after meta-training, is strong meta-generalization: the ability to apply the optimizers to new tasks. Recent state-of-the-art work in learned optimizers, VeLO (Metz et al., 2022), requires a large number of highly diverse meta-training tasks along with massive computational resources, 4000 TPU months, to achieve meta-generalization. This makes further improvements to such learned optimizers impractical. In this work, we identify several key elements in learned optimizer architectures and meta-training procedures that can lead to strong meta-generalization. We also propose evaluation metrics to reliably assess quantitative performance of an optimizer at scale on a set of evaluation tasks. Our proposed approach, Celo, makes a significant leap in improving the meta-generalization performance of learned optimizers and also outperforms tuned state-of-the-art optimizers on a diverse set of out-of-distribution tasks, despite being meta-trained for just 24 GPU hours.
format Preprint
id arxiv_https___arxiv_org_abs_2501_12670
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Celo: Training Versatile Learned Optimizers on a Compute Diet
Moudgil, Abhinav
Knyazev, Boris
Lajoie, Guillaume
Belilovsky, Eugene
Machine Learning
Learned optimization has emerged as a promising alternative to hand-crafted optimizers, with the potential to discover stronger learned update rules that enable faster, hyperparameter-free training of neural networks. A critical element for practically useful learned optimizers, that can be used off-the-shelf after meta-training, is strong meta-generalization: the ability to apply the optimizers to new tasks. Recent state-of-the-art work in learned optimizers, VeLO (Metz et al., 2022), requires a large number of highly diverse meta-training tasks along with massive computational resources, 4000 TPU months, to achieve meta-generalization. This makes further improvements to such learned optimizers impractical. In this work, we identify several key elements in learned optimizer architectures and meta-training procedures that can lead to strong meta-generalization. We also propose evaluation metrics to reliably assess quantitative performance of an optimizer at scale on a set of evaluation tasks. Our proposed approach, Celo, makes a significant leap in improving the meta-generalization performance of learned optimizers and also outperforms tuned state-of-the-art optimizers on a diverse set of out-of-distribution tasks, despite being meta-trained for just 24 GPU hours.
title Celo: Training Versatile Learned Optimizers on a Compute Diet
topic Machine Learning
url https://arxiv.org/abs/2501.12670