SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1907.00959 · 2019

Single-Path Mobile AutoML: Efficient ConvNet Design and NAS Hyperparameter Optimization

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

Can we reduce the search cost of Neural Architecture Search (NAS) from days down to only few hours? NAS methods automate the design of Convolutional Networks (ConvNets) under hardware constraints and they have emerged as key components of AutoML frameworks. However, the NAS problem remains challenging due to the combinatorially large design space and the significant search time (at least 200 GPU-hours). In this work, we alleviate the NAS search cost down to less than 3 hours, while achieving state-of-the-art image classification results under mobile latency constraints. We propose a novel differentiable NAS formulation, namely Single-Path NAS, that uses one single-path over-parameterized ConvNet to encode all architectural decisions based on shared convolutional kernel parameters, hence drastically decreasing the search overhead. Single-Path NAS achieves state-of-the-art top-1 ImageNet accuracy (75.62%), hence outperforming existing mobile NAS methods in similar latency settings (~80ms). In particular, we enhance the accuracy-runtime trade-off in differentiable NAS by treating the Squeeze-and-Excitation path as a fully searchable operation with our novel single-path encoding. Our method has an overall cost of only 8 epochs (24 TPU-hours), which is up to 5,000x faster compared to prior work. Moreover, we study how different NAS formulation choices affect the performance of the designed ConvNets. Furthermore, we exploit the efficiency of our method to answer an interesting question: instead of empirically tuning the hyperparameters of the NAS solver (as in prior work), can we automatically find the hyperparameter values that yield the desired accuracy-runtime trade-off? We open-source our entire codebase at: https://github.com/dstamoulis/single-path-nas.

For agents

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

get_harvested_code_for_paper("1907.00959")
get_code_for_paper("1907.00959")
have("1907.00959")

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

curl https://syntology.ai/api/ran/1907.00959.json

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

[![Syntology run record](https://syntology.ai/api/ran/1907.00959.svg)](https://syntology.ai/paper/1907.00959)

Connect an agent — have() is free.