Dropout-based Automatic Relevance Determination

By M. Dmitry, A. Arseniy, V. Dmitry. 2016

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Jiri Hron
2. Kirill Neklyudov
3. Arsenii Ashukha
4. Yarin Gal
5. Dmitry P. Vetrov
6. Dmitry Molchanov
7. Alex Kendall
8. Kumar Shridhar

Citations in the corpus

• Concrete Dropout (2017, methodology): “We chose not to compare to Gaussian dropout in our experiments, as when optimising Gaussian dropout’s ↵ following its variational interpretation [23], the method is known to underperform [28] (however, Gal [7] compared Gaussian dropout to Bernoulli dropout and found that when optimising the dropout ”
• Structured Bayesian Pruning via Log-Normal Multiplicative Noise (2017, methodology): “Sparsity can also be induced by using the Sparse Bayesian Learning framework with empirical Bayes [21] or with sparsity-inducing priors [12, 15, 16].”