Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture Search
This work addresses the computational inefficiency of neural architecture search for GANs, which is a domain-specific problem for researchers and practitioners in generative modeling.
The paper tackles the problem of efficiently searching for optimal GAN architectures by introducing a reinforcement learning method that formulates the search as a Markov decision process, achieving competitive image generation results on CIFAR-10 and STL-10 with a computational cost of only 7 GPU hours.
In this paper, we introduce a new reinforcement learning (RL) based neural architecture search (NAS) methodology for effective and efficient generative adversarial network (GAN) architecture search. The key idea is to formulate the GAN architecture search problem as a Markov decision process (MDP) for smoother architecture sampling, which enables a more effective RL-based search algorithm by targeting the potential global optimal architecture. To improve efficiency, we exploit an off-policy GAN architecture search algorithm that makes efficient use of the samples generated by previous policies. Evaluation on two standard benchmark datasets (i.e., CIFAR-10 and STL-10) demonstrates that the proposed method is able to discover highly competitive architectures for generally better image generation results with a considerably reduced computational burden: 7 GPU hours. Our code is available at https://github.com/Yuantian013/E2GAN.