# Neural Architecture Search Over a Graph Search Space

@article{Laroussilhe2018NeuralAS, title={Neural Architecture Search Over a Graph Search Space}, author={Quentin de Laroussilhe and Stanislaw Jastrzebski and Neil Houlsby and Andrea Gesmundo}, journal={ArXiv}, year={2018}, volume={abs/1812.10666} }

Neural architecture search (NAS) enabled the discovery of state-of-the-art architectures in many domains. However, the success of NAS depends on the definition of the search space, i.e. the set of the possible to generate neural architectures. State-of-the-art search spaces are defined as a static sequence of decisions and a set of available actions for each decision, where each possible sequence of actions defines an architecture. We propose a more expressive formulation of NAS, using a graph… CONTINUE READING

Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

2

Twitter Mentions

#### Citations

##### Publications citing this paper.

## Transfer NAS: Knowledge Transfer between Search Spaces with Transformer Agents

VIEW 2 EXCERPTS

CITES BACKGROUND

#### References

##### Publications referenced by this paper.

SHOWING 1-10 OF 26 REFERENCES

## Neural Architecture Search with Reinforcement Learning

VIEW 7 EXCERPTS

HIGHLY INFLUENTIAL

## Raiders of the Lost Architecture: Kernels for Bayesian Optimization in Conditional Parameter Spaces

VIEW 7 EXCERPTS

HIGHLY INFLUENTIAL

## Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

VIEW 2 EXCERPTS

HIGHLY INFLUENTIAL

## Transfer Automatic Machine Learning

VIEW 1 EXCERPT