Generative Adversarial Neural Architecture Search
Despite the empirical success of neural architecture search (NAS) in deep learning applications, the optimality, reproducibility and cost of NAS schemes remain hard to assess. In this paper, we propose Generative Adversarial NAS (GA-NAS) with theoretically provable convergence guarantees, promoting stability and reproducibility in neural architecture search. Inspired by importance sampling, GA-NAS iteratively fits a generator to previously discovered top architectures, thus increasingly focusing on important parts of a large search space. Furthermore, we propose an efficient adversarial learning approach, where the generator is trained by reinforcement learning based on rewards provided by a discriminator, thus being able to explore the search space without evaluating a large number of architectures. Extensive experiments show that GA-NAS beats the best published results under several cases on three public NAS benchmarks. In the meantime, GA-NAS can handle ad-hoc search constraints and search spaces. We show that GA-NAS can be used to improve already optimized baselines found by other NAS methods, including EfficientNet and ProxylessNAS, in terms of ImageNet accuracy or the number of parameters, in their original search space.
Code (0)
등록된 구현이 없습니다.
Tasks
Neural Architecture SearchMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
AdversarialNAS: Adversarial Neural Architecture Search for GANs
Neural Architecture Search (NAS) that aims to automate the procedure of architecture design has achieved promising results in many computer vision fields. In this paper, we propose an AdversarialNAS method specially tail…
GPUImage GenerationNeural Architecture SearchUnconditional Image GenerationEGANS: Evolutionary Generative Adversarial Network Search for Zero-Shot Learning
Zero-shot learning (ZSL) aims to recognize the novel classes which cannot be collected for training a prediction model. Accordingly, generative models (e.g., generative adversarial network (GAN)) are typically used to sy…
Generative Adversarial NetworkNeural Architecture SearchZero-Shot LearningAlphaGAN: Fully Differentiable Architecture Search for Generative Adversarial Networks
Generative Adversarial Networks (GANs) are formulated as minimax game problems, whereby generators attempt to approach real data distributions by virtue of adversarial learning against discriminators. The intrinsic probl…
GPUAlphaGAN: Fully Differentiable Architecture Searchfor Generative Adversarial Networks
Generative Adversarial Networks (GANs) are formulated as minimax game problems, whereby generators attempt to approach real data distributions by virtue of adversarial learning against discriminators. In this work, we ai…
GPUAGAN: Towards Automated Design of Generative Adversarial Networks
Recent progress in Generative Adversarial Networks (GANs) has shown promising signs of improving GAN training via architectural change. Despite some early success, at present the design of GAN architectures requires huma…
image-classificationImage ClassificationImage GenerationNeural Architecture Search