Distilling Intractable Generative Models
By George Papamakarios, Iain Murray. 2015
14 citations recorded by the source corpus.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- George Papamakarios
- Iain Murray
- Charles Sutton
- Yoshua Bengio
- Kai Xu
- Ruslan Salakhutdinov
- Theo Pavlakou
- Dae Hoon Park
Citations in the corpus
- Interpreting Deep Classifier by Visual Distillation of Dark Knowledge (2018, methodology): “Instead of using common choices for D suggested in the model compression literature, such as KL divergence and Jensen-Shannon (JS) divergence (Papamakarios & Murray, 2015), we empirically found that more informative visualizations arose from the symmetric KL divergence where”
- Masked Autoregressive Flow for Density Estimation (2017, methodology): “e inference, conditional density estimators can learn models for the likelihood [7] or the posterior [26] from simulated data. Density estimators can learn effective proposals for importance sampling [25] or sequential Monte Carlo [11, 24]; such proposals can be used in probabilistic programming env”
- Fast $\epsilon$-free Inference of Simulation Models with Bayesian Conditional Density Estimation (2016, methodology): “Neural density estimators have been employed in learning proposal distributions for importance sampling [20] and Sequential Monte Carlo [9, 19].”