Deep Randomized Distributed Function Computation (DeepRDFC): Neural Distributed Channel Simulation
This work addresses distributed computation and learning applications, especially when common randomness is limited and strong function computation guarantees are needed, representing an incremental advancement by applying deep learning to an existing framework.
The paper tackles the problem of simulating an unknown target distribution in the randomized distributed function computation (RDFC) framework using only data samples, achieving significantly high performance with communication load gains compared to data compression methods.
The randomized distributed function computation (RDFC) framework, which unifies many cutting-edge distributed computation and learning applications, is considered. An autoencoder (AE) architecture is proposed to minimize the total variation distance between the probability distribution simulated by the AE outputs and an unknown target distribution, using only data samples. We illustrate significantly high RDFC performance with communication load gains from our AEs compared to data compression methods. Our designs establish deep learning-based RDFC methods and aim to facilitate the use of RDFC methods, especially when the amount of common randomness is limited and strong function computation guarantees are required.