SCHOLARLY PUBLICATION ✓ Open Access

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

Petro B. Liashchynskyi, Pavlo B. Liashchynskyi

📖 arXiv (Cornell University) 📅 2019-12-12 🔗 DOI: 10.48550/arxiv.1912.06059

📄 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.

📄 Abstract

📤 Share this page

🔬 Related Research Papers

fastMRI: An Open Dataset and Benchmarks for Accelerated MRI

GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding

Deep Neural Networks as Gaussian Processes

Modern hierarchical, agglomerative clustering algorithms

KAN: Kolmogorov-Arnold Networks

Sanity Checks for Saliency Maps

Texture Networks: Feed-forward Synthesis of Textures and Stylized Images

SNIP: Single-shot Network Pruning based on Connection Sensitivity

The relativistic discriminator: a key element missing from standard GAN

The Hidden Vulnerability of Distributed Learning in Byzantium

Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning

FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting