REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models

Advances in Neural Information Processing Systems

Volumn 2017-December, Issue , 2017, Pages 2628-2637

  Tucker, George ^a   Mnih, Andriy ^b   Maddison, Chris J ^b,c   Lawson, Dieterich ^a   Sohl Dickstein, Jascha ^a  

^a GOOGLE INC   (United States)

^b DEEPMIND   (United Kingdom)

^c UNIVERSITY OF OXFORD   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

MONTE CARLO METHODS;

CONTINUOUS RELAXATION; DISCRETE VARIABLES; FASTER CONVERGENCE; GRADIENT ESTIMATES; GRADIENT ESTIMATOR; LATENT VARIABLE MODELS; STATE OF THE ART; VARIANCE REDUCTIONS;

EQUIVALENCE CLASSES;

EID: 85046959617     PISSN: 10495258     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (24)

1. Yuri Burda, Roger Grosse, and Ruslan Salakhutdinov. Importance weighted autoencoders. arXiv preprint arXiv:1509.00519 2015.
2. Michael C Fu. Gradient estimation. Handbooks in operations research and management science, 13: 575-616, 2006.
3. Peter W Glynn. Likelihood ratio gradient estimation for stochastic systems. Communications of the ACM, 33(10):75-84, 1990.
4. Shixiang Gu, Sergey Levine, Ilya Sutskever, and Andriy Mnih. Muprop: Unbiased backpropagation for stochastic neural networks. arXiv preprint arXiv:1511.05176 2015.
5. Eric Jang, Shixiang Gu, and Ben Poole. Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:1611.01144 2016.
6. Diederik Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 2014.
7. Diederik P Kingma and Max Welling. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 2013.
8. ∗ Sampling. In Advances in Neural Information Processing Systems 27, 2014.
9. Chris J Maddison, Andriy Mnih, and Yee Whye Teh. The concrete distribution: A continuous relaxation of discrete random variables. arXiv preprint arXiv:1611.00712 2016.
10. Andriy Mnih and Karol Gregor. Neural variational inference and learning in belief networks. In Proceedings of The 31st International Conference on Machine Learning, pp. 1791-1799, 2014.
11. Andriy Mnih and Danilo Rezende. Variational inference for monte carlo objectives. In Proceedings of The 33rd International Conference on Machine Learning, pp. 2188-2196, 2016.
12. Volodymyr Mnih, Nicolas Heess, Alex Graves, et al. Recurrent models of visual attention. In Advances in neural information processing systems, pp. 2204-2212, 2014.
13. Art B. Owen. Monte Carlo theory, methods and examples. 2013.
14. John Paisley, David M Blei, and Michael I Jordan. Variational bayesian inference with stochastic search. In Proceedings of the 29th International Coference on International Conference on Machine Learning, pp. 1363-1370, 2012.
15. Tapani Raiko, Mathias Berglund, Guillaume Alain, and Laurent Dinh. Techniques for learning binary stochastic feedforward neural networks. arXiv preprint arXiv:1406.2989 2014.
16. Rajesh Ranganath, Sean Gerrish, and David M Blei. Black box variational inference. In AISTATS, pp. 814-822, 2014.
17. Danilo Jimenez Rezende, Shakir Mohamed, and Daan Wierstra. Stochastic backpropagation and approximate inference in deep generative models. In Proceedings of The 31st International Conference on Machine Learning, pp. 1278-1286, 2014.
18. Geoffrey Roeder, Yuhuai Wu, and David Duvenaud. Sticking the landing: An asymptotically zero-variance gradient estimator for variational inference. arXiv preprint arXiv:1703.09194 2017.
19. Francisco JR Ruiz, Michalis K Titsias, and David M Blei. Overdispersed black-box variational inference. In Proceedings of the Thirty-Second Conference on Uncertainty in Artificial Intelligence, pp. 647-656. AUAI Press, 2016.
20. Ruslan Salakhutdinov and Iain Murray. On the quantitative analysis of deep belief networks. In Proceedings of the 25th international conference on Machine learning, pp. 872-879. ACM, 2008.
21. Michalis K Titsias and Miguel Lázaro-Gredilla. Local expectation gradients for black box variational inference. In Advances in Neural Information Processing Systems, pp. 2638-2646, 2015.
22. Ronald J Williams. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning, 8(3-4):229-256, 1992.
23. David Wingate and Theophane Weber. Automated variational inference in probabilistic programming. arXiv preprint arXiv:1301.1299 2013.
24. Wojciech Zaremba and Ilya Sutskever. Reinforcement learning neural Turing machines. arXiv preprint arXiv:1505.00521, 362, 2015.