Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2507.16533 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913953166131200 |
|---|---|
| author | Jha, Abhash Kumar Moradian, Shakiba Krishnakumar, Arjun Rapp, Martin Hutter, Frank |
| author_facet | Jha, Abhash Kumar Moradian, Shakiba Krishnakumar, Arjun Rapp, Martin Hutter, Frank |
| contents | Gradient-based one-shot neural architecture search (NAS) has significantly reduced the cost of exploring architectural spaces with discrete design choices, such as selecting operations within a model. However, the field faces two major challenges. First, evaluations of gradient-based NAS methods heavily rely on the DARTS benchmark, despite the existence of other available benchmarks. This overreliance has led to saturation, with reported improvements often falling within the margin of noise. Second, implementations of gradient-based one-shot NAS methods are fragmented across disparate repositories, complicating fair and reproducible comparisons and further development. In this paper, we introduce Configurable Optimizer (confopt), an extensible library designed to streamline the development and evaluation of gradient-based one-shot NAS methods. Confopt provides a minimal API that makes it easy for users to integrate new search spaces, while also supporting the decomposition of NAS optimizers into their core components. We use this framework to create a suite of new DARTS-based benchmarks, and combine them with a novel evaluation protocol to reveal a critical flaw in how gradient-based one-shot NAS methods are currently assessed. The code can be found at https://github.com/automl/ConfigurableOptimizer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_16533 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | confopt: A Library for Implementation and Evaluation of Gradient-based One-Shot NAS Methods Jha, Abhash Kumar Moradian, Shakiba Krishnakumar, Arjun Rapp, Martin Hutter, Frank Machine Learning Artificial Intelligence 68T01 I.2.6 Gradient-based one-shot neural architecture search (NAS) has significantly reduced the cost of exploring architectural spaces with discrete design choices, such as selecting operations within a model. However, the field faces two major challenges. First, evaluations of gradient-based NAS methods heavily rely on the DARTS benchmark, despite the existence of other available benchmarks. This overreliance has led to saturation, with reported improvements often falling within the margin of noise. Second, implementations of gradient-based one-shot NAS methods are fragmented across disparate repositories, complicating fair and reproducible comparisons and further development. In this paper, we introduce Configurable Optimizer (confopt), an extensible library designed to streamline the development and evaluation of gradient-based one-shot NAS methods. Confopt provides a minimal API that makes it easy for users to integrate new search spaces, while also supporting the decomposition of NAS optimizers into their core components. We use this framework to create a suite of new DARTS-based benchmarks, and combine them with a novel evaluation protocol to reveal a critical flaw in how gradient-based one-shot NAS methods are currently assessed. The code can be found at https://github.com/automl/ConfigurableOptimizer. |
| title | confopt: A Library for Implementation and Evaluation of Gradient-based One-Shot NAS Methods |
| topic | Machine Learning Artificial Intelligence 68T01 I.2.6 |
| url | https://arxiv.org/abs/2507.16533 |