Pith. sign in

REVIEW 4 cited by

Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1807.06906 v1 pith:GTAF4677 submitted 2018-07-18 cs.LG cs.AIcs.CVstat.ML

Arber Zela , Aaron Klein , Stefan Falkner , Frank Hutter This is my paper
classification cs.LGcs.AIcs.CVstat.ML
keywords architecturehyperparameterneuralsearchdemonstrateduringefficientepochs
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

While existing work on neural architecture search (NAS) tunes hyperparameters in a separate post-processing step, we demonstrate that architectural choices and other hyperparameter settings interact in a way that can render this separation suboptimal. Likewise, we demonstrate that the common practice of using very few epochs during the main NAS and much larger numbers of epochs during a post-processing step is inefficient due to little correlation in the relative rankings for these two training regimes. To combat both of these problems, we propose to use a recent combination of Bayesian optimization and Hyperband for efficient joint neural architecture and hyperparameter search.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Fault Localisation and Repair for DL Systems: An Empirical Study with LLMs

    cs.SE 2025-06 conditional novelty 6.0 of 10

    LLMs, especially GPT-4, outperform existing fault localisation and repair tools for deep learning models in accuracy, speed, and stability.

  2. Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive

    cs.CL 2024-02 conditional novelty 6.0 of 10

    DPOP is a new loss function that prevents DPO from lowering preferred response likelihoods and outperforms standard DPO on diverse datasets, MT-Bench, and enables Smaug-72B to exceed 80% on the Open LLM Leaderboard.

  3. You Only Train Once

    cs.LG 2025-06 conditional novelty 4.0 of 10

    YOTO learns loss weights via a softmax-parameterized gradient update during training, outperforming fixed grid-searched weights on two vision benchmarks.

  4. Spiking Neural Network Architecture Search: A Survey

    cs.NE 2025-10 unverdicted novelty 2.0 of 10

    A survey of Spiking Neural Network architecture search techniques viewed through a hardware/software co-design lens.

Pith tools