LGNEMLDec 12, 2019

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

arXiv:1912.06059v1749 citations
Originality Synthesis-oriented
AI Analysis

This is an incremental comparison of existing hyperparameter optimization methods applied to NAS, relevant for researchers in automated machine learning.

The paper compared Grid Search, Random Search, and Genetic Algorithms for neural architecture search on CIFAR-10, finding differences in execution time and model accuracy.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes