Corpus ID: 202540141

Best Practices for Scientific Research on Neural Architecture Search

@article{Lindauer2019BestPF,
  title={Best Practices for Scientific Research on Neural Architecture Search},
  author={M. Lindauer and F. Hutter},
  journal={ArXiv},
  year={2019},
  volume={abs/1909.02453}
}
  • M. Lindauer, F. Hutter
  • Published 2019
  • Mathematics, Computer Science
  • ArXiv
  • 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 major strides in developing better NAS methods, the quality of scientific empirical evaluations in the young field of NAS is still lacking behind that of other areas of machine learning. To address this issue, we describe a set of possible issues and ways to… CONTINUE READING

    Topics from this paper.

    ONE-SHOT NEURAL ARCHITECTURE SEARCH
    An Introduction to Neural Architecture Search for Convolutional Networks
    NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture Search
    • 25
    • PDF
    NAS evaluation is frustratingly hard
    • 36
    • PDF
    A Study on Encodings for Neural Architecture Search
    • 3
    • Highly Influenced
    • PDF
    NATS-Bench: Benchmarking NAS algorithms for Architecture Topology and Size
    Multi-fidelity Neural Architecture Search with Knowledge Distillation
    • 1
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 31 REFERENCES
    NAS-Bench-101: Towards Reproducible Neural Architecture Search
    • 99
    • PDF
    Neural Architecture Search
    • 24
    • PDF
    Random Search and Reproducibility for Neural Architecture Search
    • 186
    • PDF
    Neural Architecture Search with Reinforcement Learning
    • 1,921
    • PDF
    DARTS: Differentiable Architecture Search
    • 904
    • Highly Influential
    • PDF
    Tabular Benchmarks for Joint Architecture and Hyperparameter Optimization
    • 17
    • PDF
    The Evolved Transformer
    • 111
    • PDF
    Shake-Shake regularization
    • 214
    • PDF