Showing 2024Show all
3 papers · 1 filter
cs.LG2024
Federated Prediction-Powered Inference from Decentralized Data
Ping Luo, Xiaoge Deng, Ziqing Wen +2
In various domains, the increasing application of machine learning allows researchers to access inexpensive predictive data, which can be utilized as auxiliary data for statistical…
cs.LG2024
Adaptive Momentum Benefits Score-based Generative Models
Ziqing Wen, Xiaoge Deng, Ping Luo +3
Score-based Generative Models (SGMs) have achieved remarkable success in generation tasks by establishing a diffusion process that gradually perturbs real data into Gaussian noise…
cs.LG2024
Accelerating Federated Learning by Selecting Beneficial Herd of Local Gradients
Ping Luo, Xiaoge Deng, Ziqing Wen +2
Federated Learning (FL) is a distributed machine learning framework in communication network systems. However, the systems' Non-Independent and Identically Distributed (Non-IID) da…