← Back to all news
arXiv Machine Learning By Filip Kova\v{c}evi\'c, Edwige Cyffers, Stefano Sarao Mannelli, Marco Mondelli

High-Dimensional Asymptotics and Dataset Selection for Private Transfer Learning

Read the original on arXiv Machine Learning →

The paper addresses the challenge of selecting external datasets for private transfer learning by modeling high‑dimensional regression with heterogeneous sources and a weighted ridge estimator. It relies solely on aggregated statistics and offers privacy guarantees under $ ho$‑zero‑concentrated differential privacy for labels or both features and labels. A deterministic equivalent of test error is derived, enabling optimization of hyperparameters and decision‑making about the utility of private external data without accessing individual records.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Oct 2

Certification-Based Differentially Private Learning

The paper extends the abstract gradient training (AGT) framework to provide tighter differential privacy guarantees for both private prediction and private learning. It introduces Abstract Gradient Sampling (AGS) to analyze privacy in continuous, unbounded regression and offers theoretical and empirical evidence that these methods yield tighter bounds than global-sensitivity baselines, even in previously unbounded settings. The authors also demonstrate that their private learning algorithm can outperform standard private learners under comparable conditions.

By Mihnea Ghitu, Matthew Wicker
benchmarkssafety
More like this →