SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.00153 · 2024

$μ$LO: Compute-Efficient Meta-Generalization of Learned Optimizers

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Learned optimizers (LOs) have the potential to significantly reduce the wall-clock training time of neural networks. However, they can struggle to optimize unseen tasks (meta-generalize), especially when training networks wider than those seen during meta-training. To address this, we derive the Maximal Update Parametrization ($μ$P) for two state-of-the-art learned optimizer architectures and propose a simple meta-training recipe for $μ$-parameterized LOs ($μ$LOs). Our empirical evaluation demonstrates that LOs meta-trained with our recipe substantially improve meta-generalization to wider unseen tasks when compared to LOs trained under standard parametrization (SP) using the same compute budget. We also empirically observe that $μ$LOs exhibit unexpectedly improved meta-generalization to deeper networks ($5\times$ meta-training) and surprising generalization to much longer training horizons ($25\times$ meta-training) when compared to SP LOs.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2406.00153")
get_code_for_paper("2406.00153")
have("2406.00153")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2406.00153.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2406.00153.svg)](https://syntology.ai/paper/2406.00153)

Connect an agent — have() is free.