Double Oracle Neural Architecture Search for Game Theoretic Deep Learning Models
Institute for Infocomm Research, Agency for Science, Technology and Research (A*STAR)(新加坡科技研究局信息通信研究院);School of Computer Science and Engineering, Nanyang Technological University(南洋理工大学计算机科学与工程学院);KTH Royal Institute of Technology(瑞典皇家理工学院);University of Nebraska-Lincoln(内布拉斯加大学林肯分校);A*STAR Centre for Frontier AI Research(新加坡科技研究局前沿人工智能研究中心)
Aye Phyu Phyu Aung, Xinrun Wang, Ruiyu Wang, Hau Chan, Bo An, Xiaoli Li, J. Senthilnath
In this paper, we propose a new approach to train deep learning models using game theory concepts including Generative Adversarial Networks (GANs) and Adversarial Training (AT) where we deploy a double-oracle framework using best response oracles. GAN is essentially a two-player zero-sum game between the generator and the discriminator. The same concept can be applied to AT with attacker and classifier as players. Training these models is challenging as a pure Nash equilibrium may not exist and even finding the mixed Nash equilibrium is difficult as training algorithms for both GAN and AT have a large-scale strategy space. Extending our preliminary model DO-GAN, we propose the methods to apply the double oracle framework concept to Adversarial Neural Architecture Search (NAS for GAN) and Adversarial Training (NAS for AT) algorithms. We first generalize the players' strategies as the trained models of generator and discriminator from the best response oracles. We then compute the meta-strategies using a linear program. For scalability of the framework where multiple network models of best responses are stored in the memory, we prune the weakly-dominated players' strategies to keep the oracles from becoming intractable. Finally, we conduct experiments on MNIST, CIFAR-10 and TinyImageNet for DONAS-GAN. We also evaluate the robustness under FGSM and PGD attacks on CIFAR-10, SVHN and TinyImageNet for DONAS-AT. We show that all our variants have significant improvements in both subjective qualitative evaluation and quantitative metrics, compared with their respective base architectures.
Learning in Non-convex Games with an Optimization Oracle
Google AI Princeton(谷歌AI普林斯顿);Princeton University(普林斯顿大学)
我们认为在线学习在一个敌对的,非凸设置的假设下,学习者有一个离线的优化预言。在专家建议的一般预测设置中,Hazan et al.(2016)确定,在优化-预言模型中,在线学习需要比统计学习更多的计算。在本文中,我们表明,通过稍微加强预言机模型,在线和统计学习模型在计算上变得等价。我们的结果适用于任何Lipschitz和有界(但不一定是凸)函数。作为一个应用程序,我们演示了离线预言机如何在非凸博弈中实现均衡的有效计算,其中包括GAN(生成对抗网络)作为特例。
A Game-theoretic Framework for Privacy-preserving Federated Learning
Huazhong University of Science and Technology(华中科技大学);Webank(微众银行);MSRA(微软亚洲研究院);Tsinghua University(清华大学);Hong Kong University of Science and Technology(香港科技大学)
DO-GAN: A Double Oracle Framework for Generative Adversarial Networks
Nanyang Technological University(南洋理工大学);Institute for Infocomm Research, A*STAR(新加坡科技研究局资讯通信研究院);A*STAR Centre for Frontier AI Research(新加坡科技研究局前沿人工智能研究中心)
Deep Reinforcement Learning for Green Security Games with Real-Time Information
Peking University(北京大学);Carnegie Mellon University(卡内基梅隆大学);Stanford University(斯坦福大学);University of California, Berkeley(加州大学伯克利分校);World Wild Fund for Nature(世界自然基金会);Microsoft Research(微软研究院)