3 accepted papers
Weight binarization has emerged as a promising strategy to reduce the complexity of large language models (LLMs). Existing approaches fall into post-training binarization, which is simple but causes severe performance loss, and training-aware methods, which depend on full-precision latent weights, a…
Computational intensiveness of deep learning has motivated low-precision arithmetic designs. However, the current quantized/binarized training approaches are limited by: (1) significant performance loss due to arbitrary approximations of the latent weight gradient through its discretization/binariza…
In this paper, we propose a novel centralized Asynchronous Federated Learning (FL) framework, FAVANO for training Deep Neural Networks (DNNs) in resource-constrained environments. Despite its popularity, "classical" federated learning faces the increasingly difficult task of scaling synchronous comm…