3 citations · 5 across the 5 of their papers we have counts for
5 papers
A Generalized Meta Federated Learning Framework with Theoretical Convergence Guarantees
Mohammad Vahid Jamali, Hamid Saber, Jung Hyun Bae
Meta federated learning (FL) is a personalized variant of FL, where multiple agents collaborate on training an initial shared model without exchanging raw data samples. The initial…
Simplified Successive Cancellation List Decoding of PAC Codes
Hamid Saber, Homayoon Hatami, Jung Hyun Bae
Polar codes are the first class of structured channel codes that achieve the symmetric capacity of binary channels with efficient encoding and decoding. In 2019, Arikan proposed a…
ProductAE: Toward Deep Learning Driven Error-Correction Codes of Large Dimensions
Mohammad Vahid Jamali, Hamid Saber, Homayoon Hatami +1
While decades of theoretical research have led to the invention of several classes of error-correction codes, the design of such codes is an extremely challenging task, mostly driv…
List Autoencoder: Towards Deep Learning Based Reliable Transmission Over Noisy Channels
Hamid Saber, Homayoon Hatami, Jung Hyun Bae
In this paper, we present list autoencoder (listAE) to mimic list decoding used in classical coding theory. With listAE, the decoder network outputs a list of decoded message word…
ProductAE: Towards Training Larger Channel Codes based on Neural Product Codes
Mohammad Vahid Jamali, Hamid Saber, Homayoon Hatami +1
There have been significant research activities in recent years to automate the design of channel encoders and decoders via deep learning. Due the dimensionality challenge in chann…