Showing 2024Show all
2 papers · 1 filter
cs.LG2024
DP-2Stage: Adapting Language Models as Differentially Private Tabular Data Generators
Tejumade Afonja, Hui-Po Wang, Raouf Kerkouche +1
Generating tabular data under differential privacy (DP) protection ensures theoretical privacy guarantees but poses challenges for training machine learning models, primarily due t…
cs.LG2024
Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models
Hui-Po Wang, Mario Fritz
Despite the widespread use of statistical prior models in various fields, such models for neural network gradients have long been overlooked. The inherent challenge stems from thei…