Methods › General › Neural Architecture Search

Neural Architecture Search

20 methods 246 papers tagged archive 2025-07-28

The archive attaches this collection's text per method and the copies differ: 2 distinct texts across 20 of the 20 methods here. All are shown, most-carried first (a tie goes to the text carrying Papers with Code's collection boilerplate, then to the longer text); no vote is taken between them.

Text 1, carried by 19 of 20 methods:

Neural Architecture Search methods are search methods that seek to learn architectures for machine learning tasks, including the underlying build blocks. Below you can find a continuously updating list of neural architecture search algorithms.

Text 2, carried by 1 of 20 methods:

Hyperparameter Search methods are used to search for hyperparameters during the training stage of a neural network. Below you can find a continuously updating list of (specialized) hyperparameter search methods.

Methods

All 20 methods in this collection, most-tagged first. Year is the archive's introduced_year; the archive stores 2000 when it has none, shown here as “–”. Papers counts distinct papers the archive tags with the method. Click a heading to sort.

DARTS Differentiable Architecture Search – 143
Differentiable NAS Differentiable Neural Architecture Search – 39
Neural Architecture Search – 23
DNAS Differentiable Neural Architecture Search – 20
ProxylessNAS – 17
PNAS Progressive Neural Architecture Search – 16
Aging Evolution – 3
DetNAS – 3
AutoGAN – 2
Computation Redistribution – 1
DARTS Max-W Differentiable Architecture Search Max-W – 1
DenseNAS – 1
Differentiable Hyperparameter Search – 1
GreedyNAS – 1
Hit-Detector – 1
HyperTree MetaModel – 1
Random Mutation Search – 1
SCARLET-NAS – 1
SynaNN Synaptic Neural Network – 1
Capsule Network – 0