AI帮你理解科学

AI 生成解读视频

AI抽取解析论文重点内容自动生成视频


pub
生成解读视频

AI 溯源

AI解析本论文相关学术脉络


Master Reading Tree
生成 溯源树

AI 精读

AI抽取本论文的概要总结


微博一下
We believe that our results provide new insights into Generative Adversarial Networks training and point towards a rich algorithmic landscape to be explored in order to further understand Generative Adversarial Networks dynamics

On the Limitations of First-Order Approximation in GAN Dynamics.

ICML, pp.3011-3019, (2018)

被引用62|浏览57
EI
下载 PDF 全文
引用
微博一下

摘要

While Generative Adversarial Networks (GANs) have demonstrated promising performance on multiple vision tasks, their learning dynamics are not yet well understood, both in theory and in practice. To address this issue, we study GAN dynamics in a simple yet rich parametric model that exhibits several of the common problematic convergence...更多

代码

数据

0
简介
  • Generative Adversarial Networks (GANs) have recently been proposed as a novel framework for learning generative models (Goodfellow et al, 2014).
  • The key idea of GANs is to learn both the generative model and the loss function at the same time.
  • GANs have shown promising results on a variety of tasks, and there is a large body of work that explores the power of this framework (Goodfellow, 2017).
重点内容
  • Generative Adversarial Networks (GANs) have recently been proposed as a novel framework for learning generative models (Goodfellow et al, 2014)
  • The resulting training dynamics are usually described as a game between a generator and a discriminator
  • We provide the first rigorous proof of global convergence and show that a Generative Adversarial Networks with an optimal discriminator always converges to an approximate equilibrium
  • We haven taken a step towards a principled understanding of Generative Adversarial Networks dynamics
  • We find an interesting dichotomy: If we take optimal discriminator steps, the training dynamics provably converge
  • We believe that our results provide new insights into Generative Adversarial Networks training and point towards a rich algorithmic landscape to be explored in order to further understand Generative Adversarial Networks dynamics
方法
  • To illustrate more conclusively that the phenomena demonstrated in Figure 1 are not rare, and that first order dynamics do often fail to converge, the authors conducted the following heatmap experiments.
  • For each of these grid points, the authors randomly chose a set of initial discriminator intervals, and ran the first order dynamics for 3000 iterations, with constant stepsize 0.3
  • The authors repeated this 120 times for each grid point, and plotted the probability that the generator converged to the truth, where the authors say the generator converged to the truth if the TV distance between the generator and optimality is < 0.1.
  • The authors did the same thing for the optimal discriminator dynamics, and for unrolled discriminator dynamics with 5 unrolling steps, as described in (Metz et al, 2017), which attempt to match the optimal discriminator dynamics
结论
  • The authors haven taken a step towards a principled understanding of GAN dynamics.
  • The authors find an interesting dichotomy: If the authors take optimal discriminator steps, the training dynamics provably converge.
  • The authors show experimentally that the dynamics often fail if the authors take first order discriminator steps.
  • The authors believe that the results provide new insights into GAN training and point towards a rich algorithmic landscape to be explored in order to further understand GAN dynamics
相关工作
  • GANs have received a tremendous amount of attention over the past two years (Goodfellow, 2017). Hence we only compare our results to the most closely related papers here.

    The recent paper (Arora et al, 2017) studies generalization aspects of GANs and the existence of equilibria in the two-player game. In contrast, our paper focuses on the dynamics of GAN training. We provide the first rigorous proof of global convergence and show that a GAN with an optimal discriminator always converges to an approximate equilibrium.

    One recently proposed method for improving the convergence of GAN dynamics is the unrolled GAN (Metz et al, 2017). The paper proposes to “unroll” multiple discriminator gradient steps in the generator loss function. The authors argue that this improves the GAN dynamics by bringing the discriminator closer to an optimal discriminator response. Our experiments show that this is not a perfect approximation: the unrolled GAN still fails to converge in multiple initial configurations (however, it does converge more often than a “vanilla” one-step discriminator).
基金
  • Jerry Li was supported by NSF Award CCF-1453261 (CAREER), CCF-1565235, a Google Faculty Research Award, and an NSF Graduate Research Fellowship
  • Aleksander Madry was supported in part by an Alfred P
  • Sloan Research Fellowship, a Google Research Award, and the NSF grant CCF-1553428
  • John Peebles was supported by the NSF Graduate Research Fellowship under Grant No 1122374 and by the NSF Grant No 1065125
  • Ludwig Schmidt was supported by a Google PhD Fellowship
引用论文
  • Arjovsky, M. and Bottou, L. Towards principled methods for training generative adversarial networks. In ICLR, 2017.
    Google ScholarLocate open access versionFindings
  • Arjovsky, M., Chintala, S., and Bottou, L. Wasserstein GAN. In ICML, 2017.
    Google ScholarLocate open access versionFindings
  • Arora, S. and Zhang, Y. Do gans actually learn the distribution? an empirical study. In ICLR, 2018.
    Google ScholarLocate open access versionFindings
  • Arora, S., Ge, R., Liang, Y., Ma, T., and Zhang, Y. Generalization and equilibrium in generative adversarial nets (GANs). In ICML, 2017.
    Google ScholarLocate open access versionFindings
  • Chan, S.-O., Diakonikolas, I., Servedio, R. A., and Sun, X. Efficient density estimation via piecewise polynomial approximation. In STOC, 2014.
    Google ScholarLocate open access versionFindings
  • Devroye, L. and Lugosi, G. Combinatorial methods in density estimation. Springer Science & Business Media, 2012.
    Google ScholarFindings
  • Gautschi, W. How (un) stable are Vandermonde systems? Lecture Notes in Pure and Applied Mathematics, 124: 193–210, 1990.
    Google ScholarLocate open access versionFindings
  • Goodfellow, I. NIPS 2016 tutorial: Generative adversarial networks. CoRR, abs/1701.00160, 2017.
    Findings
  • Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. Generative adversarial nets. In NIPS, 2014.
    Google ScholarLocate open access versionFindings
  • Grnarova, P., Levy, K. Y., Lucchi, A., Hofmann, T., and Krause, A. An online learning approach to generative adversarial networks. In ICLR, 2018.
    Google ScholarLocate open access versionFindings
  • Hummel, R. and Gidas, B. Zero Crossings and the Heat Equation. New York University., 1984.
    Google ScholarFindings
  • Markov, V. On functions deviating least from zero in a given interval. Izdat. Imp. Akad. Nauk, St. Petersburg, pp. 218–258, 1892.
    Google ScholarFindings
  • Metz, L., Poole, B., Pfau, D., and Sohl-Dickstein, J. Unrolled generative adversarial networks. In ICLR, 2017.
    Google ScholarLocate open access versionFindings
  • Nagarajan, V. and Kolter, J. Z. Gradient descent gan optimization is locally stable. In NIPS, 2017.
    Google ScholarLocate open access versionFindings
您的评分 :
0

 

标签
评论
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn
小科