Neural Architecture Search with Reinforce and Masked Attention Autoregressive Density Estimators

by   Chepuri Shri Krishna, et al.

Neural Architecture Search has become a focus of the Machine Learning community. Techniques span Bayesian optimization with Gaussian priors, evolutionary learning, reinforcement learning based on policy gradient, Q-learning, and Monte-Carlo tree search. In this paper, we present a reinforcement learning algorithm based on policy gradient that uses an attention-based autoregressive model to design the policy network. We demonstrate how performance can be further improved by training an ensemble of policy networks with shared parameters, each network conditioned on a different autoregressive factorization order. On the NASBench-101 search space, it outperforms most algorithms in the literature, including random search. In particular, it outperforms RL methods based on policy gradients that use alternate architectures to specify the policy network, underscoring the importance of using masked attention in this setting. We have adhered to guidelines listed in Lindauer Hutter (2019) while designing experiments and reporting results.


BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search

Neural Architecture Search (NAS) has seen an explosion of research in th...

Policy Search with Rare Significant Events: Choosing the Right Partner to Cooperate with

This paper focuses on a class of reinforcement learning problems where s...

Resource-Constrained Neural Architecture Search on Tabular Datasets

The best neural architecture for a given machine learning problem depend...

Neural Architecture Search via Combinatorial Multi-Armed Bandit

Neural Architecture Search (NAS) has gained significant popularity as an...

Efficient Decoupled Neural Architecture Search by Structure and Operation Sampling

We propose a novel neural architecture search algorithm via reinforcemen...

Object Exchangeability in Reinforcement Learning: Extended Abstract

Although deep reinforcement learning has advanced significantly over the...

DECORE: Deep Compression with Reinforcement Learning

Deep learning has become an increasingly popular and powerful option for...

Please sign up or login with your details

Forgot password? Click here to reset