NAS-Bench-301 and the Case for Surrogate Benchmarks for Neural Architecture Search

By Julien N. Siems, Lucas Zimmer, Arber Zela, Jovita Lukasik, Margret Keuper, Frank Hutter. 2020

171 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Colin White
2. Yash Savani
3. Willie Neiswanger
4. Wuyang Chen
5. Zhangyang Wang
6. Xinyu Gong
7. Shiyu Chang
8. Sam Nolen

Citations in the corpus

• BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search (2019, methodology): “A new surrogate benchmark on the DARTS search space (Siems et al. 2020), called NASBench-301 was recently introduced.”
• Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective (2021, background): “Siems et al. (2020) studied the distribution of test error for different cell depths and numbers of parameter-free operators.”
• pTNAS: Progressive Neural Architecture Search for Tabular Data (2024, unknown): “Typically, A is characterized by multiple design dimensions, including depth (the number of layers), width (the number of channels or hidden units per layer), and macro-topology (the connectivity pattern between layers) (Ying et al., 2019; Siems et al., 2020).”