Search Results for author:
Found 2 papers, 0 papers with code
Bayesian Federated Model Compression for Communication and Computation Efficiency
We propose a decentralized Turbo variational Bayesian inference (D-Turbo-VBI) FL framework where we firstly propose a hierarchical sparse prior to promote a clustered sparse structure in the weight matrix.
Structured Bayesian Compression for Deep Neural Networks Based on The Turbo-VBI Approach
We derive an efficient Turbo-variational Bayesian inferencing (Turbo-VBI) algorithm to solve the resulting model compression problem with the proposed prior.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
