Evolutionary-Neural Hybrid Agents for Architecture Search
This work addresses the resource-intensive challenge of neural architecture search for researchers and practitioners, offering a more efficient solution, though it is incremental as it combines existing evolutionary and neural methods.
The paper tackles the problem of automating neural network design by proposing Evolutionary-Neural hybrid agents (Evo-NAS) for architecture search, achieving higher accuracy with only 1/3 of the search cost compared to common agents on a high-complexity image classification task.
Neural Architecture Search has shown potential to automate the design of neural networks. Deep Reinforcement Learning based agents can learn complex architectural patterns, as well as explore a vast and compositional search space. On the other hand, evolutionary algorithms offer higher sample efficiency, which is critical for such a resource intensive application. In order to capture the best of both worlds, we propose a class of Evolutionary-Neural hybrid agents (Evo-NAS). We show that the Evo-NAS agent outperforms both neural and evolutionary agents when applied to architecture search for a suite of text and image classification benchmarks. On a high-complexity architecture search space for image classification, the Evo-NAS agent surpasses the accuracy achieved by commonly used agents with only 1/3 of the search cost.