SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.12412 · ECCV · 2022

U-Boost NAS: Utilization-Boosted Differentiable Neural Architecture Search

Pascal Frossard, Nikolaos Dimitriadis, Ahmet Yüzügüler

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

Optimizing resource utilization in target platforms is key to achieving high performance during DNN inference. While optimizations have been proposed for inference latency, memory footprint, and energy consumption, prior hardware-aware neural architecture search (NAS) methods have omitted resource utilization, preventing DNNs to take full advantage of the target inference platforms. Modeling resource utilization efficiently and accurately is challenging, especially for widely-used array-based inference accelerators such as Google TPU. In this work, we propose a novel hardware-aware NAS framework that does not only optimize for task accuracy and inference latency, but also for resource utilization. We also propose and validate a new computational model for resource utilization in inference accelerators. By using the proposed NAS framework and the proposed resource utilization model, we achieve 2.8 -4× speedup for DNN inference compared to prior hardware-aware NAS methods while attaining similar or improved accuracy in image classification on CIFAR-10 and Imagenet-100 datasets. 1

For agents

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

get_harvested_code_for_paper("2203.12412")
get_code_for_paper("2203.12412")
have("2203.12412")

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

curl https://syntology.ai/api/ran/2203.12412.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.12412.svg)](https://syntology.ai/paper/2203.12412)

Connect an agent — have() is free.