The Library
BLOX : micro neural architecture search benchmark and algorithms
Tools
Chau, Thomas C. P., Dudziak, Lukasz, Wen, Hongkai, Lane, Nicholas Donald and Abdelfattah, Mohamed S. (2022) BLOX : micro neural architecture search benchmark and algorithms. In: 36th Conference on Neural Information Processing Systems (NeurIPS 2022), Hybrid ; New Orleans, 28 Nov - 9 Dec 2022
|
PDF
WRAP-BLOX-micro-neural-architecture-search-benchmark-algorithms-Wen-2022.pdf - Accepted Version - Requires a PDF viewer. Download (1699Kb) | Preview |
Official URL: https://openreview.net/forum?id=IIbJ9m5G73t
Abstract
Neural architecture search (NAS) has been successfully used to design numerous high-performance neural networks. However, NAS is typically compute-intensive, so most existing approaches restrict the search to decide the operations and topological structure of a single block only, then the same block is stacked repeatedly to form an end-to-end model. Although such an approach reduces the size of search space, recent studies show that a macro search space, which allows blocks in a model to be different, can lead to better performance. To provide a systematic study of the performance of NAS algorithms on a macro search space, we release Blox – a benchmark that consists of 91k unique models trained on the CIFAR-100 dataset. The dataset also includes runtime measurements of all the models on a diverse set of hardware platforms. We perform extensive experiments to compare existing algorithms that are well studied on cell-based search spaces, with the emerging blockwise approaches that aim to make NAS scalable to much larger macro search spaces. The Blox benchmark and code are available at https://github.com/SamsungLabs/blox.
Item Type: | Conference Item (Paper) | ||||||
---|---|---|---|---|---|---|---|
Subjects: | Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software | ||||||
Divisions: | Faculty of Science, Engineering and Medicine > Science > Computer Science | ||||||
Library of Congress Subject Headings (LCSH): | Neural networks (Computer science), Deep learning (Machine learning), Algorithms | ||||||
Official Date: | 2022 | ||||||
Dates: |
|
||||||
Status: | Peer Reviewed | ||||||
Publication Status: | Published | ||||||
Access rights to Published version: | Open Access (Creative Commons) | ||||||
Description: | 36th Conference on Neural Information Processing Systems (NeurIPS 2022) Track on Datasets and Benchmarks. |
||||||
Date of first compliant deposit: | 13 October 2022 | ||||||
Date of first compliant Open Access: | 14 October 2022 | ||||||
Conference Paper Type: | Paper | ||||||
Title of Event: | 36th Conference on Neural Information Processing Systems (NeurIPS 2022) | ||||||
Type of Event: | Conference | ||||||
Location of Event: | Hybrid ; New Orleans | ||||||
Date(s) of Event: | 28 Nov - 9 Dec 2022 | ||||||
Related URLs: | |||||||
Open Access Version: |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |
Downloads
Downloads per month over past year