SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.06120 · 2020

Can weight sharing outperform random architecture search? An investigation with TuNAS

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

Efficient Neural Architecture Search methods based on weight sharing have shown good promise in democratizing Neural Architecture Search for computer vision models. There is, however, an ongoing debate whether these efficient methods are significantly better than random search. Here we perform a thorough comparison between efficient and random search methods on a family of progressively larger and more challenging search spaces for image classification and detection on ImageNet and COCO. While the efficacies of both methods are problem-dependent, our experiments demonstrate that there are large, realistic tasks where efficient search methods can provide substantial gains over random search. In addition, we propose and evaluate techniques which improve the quality of searched architectures and reduce the need for manual hyper-parameter tuning. Source code and experiment data are available at https://github.com/google-research/google-research/tree/master/tunas

For agents

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

get_harvested_code_for_paper("2008.06120")
get_code_for_paper("2008.06120")
have("2008.06120")

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

curl https://syntology.ai/api/ran/2008.06120.json

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

[![Syntology run record](https://syntology.ai/api/ran/2008.06120.svg)](https://syntology.ai/paper/2008.06120)

Connect an agent — have() is free.