Frank Hutter

Best Practices for Scientific Research on Neural Architecture Search

2020 · Journal of Machine Learning Research

Finding a well-performing architecture is often tedious for both DL practitioners and researchers, leading to tremendous interest in the automation of this task by means of neural architecture search (NAS). Although the community has made …

NAS-Bench-x11 and the power of learning curves

2021 · FreiDok plus (Universitätsbibliothek Freiburg)

While early research in neural architecture search (NAS) required extreme computational resources, the recent releases of tabular and surrogate benchmarks have greatly increased the speed and reproducibility of NAS research. However, two of the most …

NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural\n Architecture Search

2020 · arXiv (Cornell University)

One-shot neural architecture search (NAS) has played a crucial role in making\nNAS methods computationally feasible in practice. Nevertheless, there is still\na lack of understanding on how these weight-sharing algorithms exactly work due\nto the many factors …

EquiTabPFN: A Target-Permutation Equivariant Prior Fitted Network

2025 · HAL (Le Centre pour la Communication Scientifique Directe)

International audience