Stochastic Digital Backpropagation

MuProp: Unbiased Backpropagation for Stochastic Neural Networks

Deep neural networks are powerful parametric models that can be trained efficiently using the backpropagation algorithm. Stochastic neural networks combine the power of large parametric functions with that of graphical models, which makes it possible to learn very complex distributions. However, as backpropagation is not directly applicable to stochastic networks that include discrete sampling ...

Stochastic Backpropagation through Mixture Density Distributions

The ability to backpropagate stochastic gradients through continuous latent distributions has been crucial to the emergence of variational autoencoders [4, 6, 7, 3] and stochastic gradient variational Bayes [2, 5, 1]. The key ingredient is an unbiased and low-variance way of estimating gradients with respect to distribution parameters from gradients evaluated at distribution samples. The “repar...

Polarization-Mode Dispersion Aware Digital Backpropagation

We study a modified DBP algorithm that accounts for PMD. Based on the accumulated PMD at the receiver, the algorithm distributively compensates for PMD in the reverse propagation and outperforms the conventional approach by up to 2.1 dB.

Digital backpropagation accounting for polarization-mode dispersion.

Digital backpropagation (DBP) is a promising digital-domain technique to mitigate Kerr-induced nonlinear interference. While it successfully removes deterministic signal-signal interactions, the performance of ideal DBP is limited by stochastic effects, such as polarization-mode dispersion (PMD). In this paper, we consider an ideal full-field DBP implementation and modify it to additionally acc...

Stochastic Weight Selection for Backpropagation Through Time Learning