2 papers
cs.IT2024
Multi-User SR-LDPC Codes via Coded Demixing with Applications to Cell-Free Systems
Jamison R. Ebert, Jean-Francois Chamberland, Krishna R. Narayanan
Novel sparse regression LDPC (SR-LDPC) codes exhibit excellent performance over additive white Gaussian noise (AWGN) channels in part due to their natural provision of shaping gain…
cs.IT2023
PolarAir: A Compressed Sensing Scheme for Over-the-Air Federated Learning
Michail Gkagkos, Krishna R. Narayanan, Jean-Francois Chamberland +1
We explore a scheme that enables the training of a deep neural network in a Federated Learning configuration over an additive white Gaussian noise channel. The goal is to create a…