1 citations · 2 across the 9 of their papers we have counts for
3 papers · 1 filter
Transfer Calibrated Prediction Powered Inference
Aditya T. Vadlamani, Jae Ho Chang, Srinivasan Parthasarathy +1
Prediction-powered inference (PPI) and its power-tuned extension (PPI++) improve confidence intervals by combining a small gold-standard labeled sample with a large AI model's pred…
Personalized Federated Learning via Variance-Aware Nonparametric Empirical Bayes
Jae Ho Chang, Arnab Auddy, Subhadeep Paul
We develop a new approach to Personalized Federated Learning across heterogeneous clients using Nonparametric Empirical Bayes (NPEB). Leveraging the asymptotic normality of local p…
Statistical Limits and Efficient Algorithms for Differentially Private Federated Learning
Arnab Auddy, Xiangni Peng, Subhadeep Paul
Federated Learning is a leading framework for training ML and AI models collaboratively across numerous user devices or databases. We study the trade-offs among estimation accuracy…