Section: New Results
Axis 2: PAC-Bayesian binary activated deep neural networks
Participant: Pascal Germain, Benjamin Guedj
We present a comprehensive study of multilayer neural networks with binary activation, relying on the PAC-Bayesian theory. Our contributions are twofold: (i) we develop an end-to-end framework to train a binary activated deep neural network, overcoming the fact that binary activation function is non-differentiable; (ii) we provide nonvacuous PAC-Bayesian generalization bounds for binary activated deep neural networks. Noteworthy, our results are obtained by minimizing the expected loss of an architecture-dependent aggregation of binary activated deep neural networks. The performance of our approach is assessed on a thorough numerical experiment protocol on real-life datasets. This work has been published in the proceedings of NeurIPS 2019 conference [35].
It is a joint work with Gaël Letarte and François Laviolette, from Université Laval (Québec, Canada).