Name
Abstract | ||
|---|---|---|
We present a variational approximation to the information bottleneck of Tishby et al. (1999). This variational approach allows us to parameterize the information bottleneck model using a neural network and leverage the reparameterization trick for efficient training. We call this method “Deep Variational Information Bottleneck”, or Deep VIB. We show that models trained with the VIB objective outperform those that are trained with other forms of regularization, in terms of generalization performance and robustness to adversarial attack. |
Year | Venue | Field |
|---|---|---|
2016 | international conference on learning representations | Robustness (computer science),Regularization (mathematics),Artificial intelligence,Information bottleneck method,Artificial neural network,Machine learning,Mathematics |
DocType | Volume | ISSN |
Journal | abs/1612.00410 | Proceedings of the International Conference on Learning
Representations (ICLR) 2017 |
Citations | PageRank | References |
20 | 0.58 | 0 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Alexander A. Alemi | 1 | 70 | 9.92 |
| Ian Fischer | 2 | 422 | 26.82 |
| Joshua V. Dillon | 3 | 50 | 3.85 |
| Michael Kuperberg | 4 | 7589 | 529.66 |