Documents
Poster
Poster
Deep Deterministic Information Bottleneck with Matrix-Based Entropy Functional
![](https://sigport.org/sites/default/files/styles/home/public/ICASSP_2021_0.jpg?itok=5O5H7jAd)
- Citation Author(s):
- Submitted by:
- Xi Yu
- Last updated:
- 22 June 2021 - 12:12pm
- Document Type:
- Poster
- Document Year:
- 2021
- Event:
- Presenters:
- Xi Yu
- Categories:
- Log in to post comments
We introduce the matrix-based Renyi’s α-order entropy functional to parameterize Tishby et al. information bottleneck (IB) principle with a neural network. We term our methodology Deep Deterministic Information Bottleneck (DIB), as it avoids variational inference and distribution assumption. We show that deep neural networks trained with DIB outperform the variational objective counterpart and those that are trained
with other forms of regularization, in terms of generalization performance and robustness to adversarial attack. Code available at
https://github.com/yuxi120407/DIB.