Year: 2025
Type: preprint
Abstract: Private machine learning introduces a trade-off between the privacy budget and training performance. Training convergence is substantially slower and extensive hyper parameter tuning is required. Consequently, efficient methods to conduct private training of models is thoroughly investigated in the literature. To this end, we investigate the strength of the data efficient model training methods in the private training setting. We adapt GLISTER (Killamsetty et al., 2021b) to the private setting and extensively assess its performance. We empirically find that practical choices of privacy budgets are too restrictive for data efficient training in the private setting.
Source: arXiv (Cornell University)
Authors: Gandhi, Ninad Jayesh, Harsha, Moparthy Venkata Subrahmanya Sri
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6966696245
Cites:
Cited by:
Related to: