Neural Joint Source-Channel Coding
Kristy Choi · Kedar Tatwawadi · Aditya Grover · Tsachy Weissman · Stefano Ermon

Tue Jun 11th 02:40 -- 03:00 PM @ Room 102

For reliable transmission across a noisy communication channel, classical results from information theory show that it is asymptotically optimal to separate out the source and channel coding processes. However, this decomposition can fall short in the finite bit-length regime, as it requires non-trivial tuning of hand-crafted codes and assumes infinite computational power for decoding. In this work, we propose to jointly learn the encoding and decoding processes using a new discrete variational autoencoder model. By adding noise into the latent codes to simulate the channel during training, we learn to both compress and error-correct given a fixed bit-length and computational budget. We obtain codes that are not only competitive against several separation schemes, but also learn useful robust representations of the data for downstream tasks such as classification. Finally, inference amortization yields an extremely fast neural decoder, almost an order of magnitude faster compared to standard decoding methods based on iterative belief propagation.

Author Information

Kristy Choi (Stanford University)
Kedar Tatwawadi (Stanford University)
Aditya Grover (Stanford University)
Tsachy Weissman (Stanford University)
Stefano Ermon (Stanford University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors