Pith. sign in

REVIEW 18 cited by

Grid Search, Random Search, Genetic Algorithm: A Big Comparison for NAS

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 1912.06059 v1 pith:HB4H6U57 submitted 2019-12-12 cs.LG cs.NEstat.ML

Petro Liashchynskyi , Pavlo Liashchynskyi This is my paper · ORCID
classification cs.LGcs.NEstat.ML
keywords searchalgorithmsalgorithmarchitecturecomparisongeneticgridneural
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In this paper, we compare the three most popular algorithms for hyperparameter optimization (Grid Search, Random Search, and Genetic Algorithm) and attempt to use them for neural architecture search (NAS). We use these algorithms for building a convolutional neural network (search architecture). Experimental results on CIFAR-10 dataset further demonstrate the performance difference between compared algorithms. The comparison results are based on the execution time of the above algorithms and accuracy of the proposed models.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 18 Pith papers

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

  1. Exploiting Structural Properties for Efficient Constraint-Aware HNSW Hyperparameter Tuning

    cs.DB 2026-07 conditional novelty 6.0 of 10

    CHAT uses HNSW-specific monotonic and unimodal structure plus resource surrogates to tune M, efc, and efs under constraints, beating black-box tuners by up to 45% throughput or 11% recall and up to 44× faster convergence.

  2. State Backdoor: Towards Stealthy Real-world Poisoning Attack on Vision-Language-Action Model in State Space

    cs.CR 2026-01 conditional novelty 6.0 of 10

    A backdoor attack on vision-language-action robot policies uses the arm's initial joint configuration as the trigger, achieving >90% triggered failure with only small clean-task degradation.

  3. Gaussian Process Methods for Very Large Astrometric Data Sets

    astro-ph.GA 2025-07 conditional novelty 6.0 of 10

    A scalable two-gaussian-process regression recovers smooth vertical profiles of mean velocity and velocity dispersion from roughly 800,000 Gaia stars, revealing mid-plane-asymmetric dispersion features interpreted as ...

  4. AIMatDesign: Knowledge-Augmented Reinforcement Learning for Inverse Materials Design under Data Scarcity

    cs.LG 2025-06 conditional novelty 6.0 of 10

    AIMatDesign uses difference-based data augmentation, LLM-guided model refinement, and knowledge-based rewards to propose Zr-based bulk metallic glasses, with one experimentally validated alloy reaching 1.7 GPa yield s...

  5. KEENHash: Hashing Programs into Function-Aware Embeddings for Large-Scale Binary Code Similarity Analysis

    cs.CR 2025-06 conditional novelty 6.0 of 10

    KEENHash hashes binaries into 8KB function-aware embeddings via LLM function embeddings, K-Means clustering, and Feature Hashing, enabling scalable program-level binary similarity analysis.

  6. Explanatory Debiasing: Involving Domain Experts in the Data Generation Process to Mitigate Representation Bias in AI Systems

    cs.HC 2024-12 conditional novelty 6.0 of 10

    Involving domain experts in AI data generation can reduce representation bias while maintaining or slightly improving model accuracy, according to a 35-participant healthcare user study.

  7. A Quality-Guided Mixture of Score-Fusion Experts Framework for Human Recognition

    cs.CV 2025-07 conditional novelty 5.0 of 10

    Quality-weighted mixture-of-experts score fusion improves whole-body biometric recognition over fixed and learned baselines across face, gait, and body modalities.

  8. Machine learning bridging battery field data and laboratory data

    stat.AP 2025-05 conditional novelty 5.0 of 10

    Two real impedance values at selected frequencies, plus state of charge and temperature, are mapped by random forests to laboratory impedance, charge/discharge, and relaxation curves, which then feed existing lab-trai...

  9. Machine learning accelerates fuel cell life testing

    stat.AP 2025-04 conditional novelty 5.0 of 10

    A fuel cell life test can be shortened to the first 1000 cycles by predicting later aging indicators from early difference curves, with reported R^2 values above 0.89.

  10. PINNsAgent: Automated PDE Surrogation with Large Language Models

    cs.CE 2025-01 conditional novelty 5.0 of 10

    An LLM-based multi-agent system that automates PINNs hyperparameter optimization, beating random and Bayesian search on 12 of 14 benchmark PDEs but only matching or beating the PINNacle benchmark on 6 of 14.

  11. LSEAD: A Privacy-Preserving LLM-Based Speech Analysis Framework for Early Alzheimer's Disease Screening

    eess.AS 2026-08 conditional novelty 4.0 of 10

    LSEAD reports 90.0% accuracy for AD versus control classification using local LLM embeddings, PCA, and logistic regression on combined ADReSS20 and ADReSSo2021 test data, and claims about 5% gains over prior published...

  12. Toward Generalizable Cognitive Impairment Detection with Speech-Based Multimodal Large Language Models

    eess.SP 2026-07 reject novelty 4.0 of 10

    A multimodal LLM pipeline (Qwen audio + Qwen text embeddings, concatenated and classified) reaches 92.4% accuracy on a combined ADReSS20/ADReSSo21 test set, but the evaluation does not justify state-of-the-art or cros...

  13. Interpretable Low-Dimensional Modeling of Spatiotemporal Agent States for Decision Making in Football Tactics

    cs.AI 2025-06 conditional novelty 4.0 of 10

    A low-dimensional, interpretable XGBoost model predicts pass success in football with F1 0.56, and identifies the distance between ball and receiver as the most important feature.

  14. VKFPos: A Learning-Based Monocular Positioning with Variational Bayesian Extended Kalman Filter Integration

    cs.CV 2025-01 conditional novelty 4.0 of 10

    A monocular positioning system that combines absolute and relative pose regression with a Kalman filter, using learned covariances, reports improved temporal accuracy on 7-Scenes and Oxford RobotCar.

  15. Automating Credit Card Limit Adjustments Using Machine Learning

    cs.LG 2025-01 conditional novelty 4.0 of 10

    An XGBoost model with cost-sensitive learning reports Cohen's kappa of 0.81 against a bank committee's credit card limit decisions and is proposed to automate the process.

  16. Fall Leaf Adversarial Attack on Traffic Sign Classification

    cs.CV 2024-11 reject novelty 4.0 of 10

    A leaf-shaped occlusion can flip some traffic sign classifications in the LISA-CNN model, but the evidence is limited to five signs and best-case placements.

  17. An introduction to Neural Networks for Physicists

    physics.ed-ph 2025-05 conditional novelty 3.0 of 10

    A teaching paper demonstrates perceptron training, PINNs, autoencoders, and SINDy on pendulum examples, with code notebooks provided online.

  18. Malware Classification using a Hybrid Hidden Markov Model-Convolutional Neural Network

    cs.LG 2024-12 conditional novelty 3.0 of 10

    Converting HMM hidden-state sequences into images and classifying them with a CNN yields 0.9781 accuracy on a 7-family Malicia subset, a 0.0023 gain over the authors' HMM-RF baseline.

Pith tools