Straight-Through Estimator as Projected Wasserstein Gradient Flow.
作者： Lawrence Carin , Chunyuan Li , Dinghan Shen , Chang Liu , Ricardo Henao
DOI:
关键词:
摘要: … gradient flow on Wasserstein space. Based upon this theoretical framework, we further propose another gradient estimator for learning discrete … We use variational autoencoder (VAE) […
arxiv.org参考文章(26)
Luigi Ambrosio, Nicola Gigli, Giuseppe Savaré, Gradient Flows: In Metric Spaces and in the Space of Probability Measures ,(2005)
Max Welling, Diederik P Kingma, Auto-Encoding Variational Bayes international conference on learning representations. ,(2014)
Phelim P. Boyle, Options: A Monte Carlo approach Journal of Financial Economics. ,vol. 4, pp. 323- 338 ,(1977) , 10.1016/0304-405X(77)90005-8
Jean-David Benamou, Yann Brenier, A computational fluid mechanics solution to the Monge-Kantorovich mass transfer problem Numerische Mathematik. ,vol. 84, pp. 375- 393 ,(2000) , 10.1007/S002110050002
Felix Otto, THE GEOMETRY OF DISSIPATIVE EVOLUTION EQUATIONS: THE POROUS MEDIUM EQUATION Pediatric Dermatology. ,vol. 26, pp. 101- 174 ,(2001) , 10.1081/PDE-100002243
, Generative Adversarial Nets neural information processing systems. ,vol. 27, pp. 2672- 2680 ,(2014) , 10.3156/JSOFT.29.5_177_2
Bernhard Schölkopf, Alex J. Smola, Karsten M. Borgwardt, Malte Rasch, Arthur Gretton, A Kernel Method for the Two-Sample-Problem neural information processing systems. ,vol. 19, pp. 513- 520 ,(2006)
Yoshua Bengio, Aaron C. Courville, Nicholas Léonard, Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation arXiv: Learning. ,(2013)
Ilya Sutskever, Andriy Mnih, Shixiang Gu, Shixiang Gu, Sergey Levine, MuProp: Unbiased Backpropagation for Stochastic Neural Networks arXiv: Learning. ,(2015)
Carl Doersch, Tutorial on Variational Autoencoders arXiv: Machine Learning. ,(2016)