@inproceedings{ris2024noise-aware,
author = {Räisä, Ossi and Markou, Stratis and Ashman, Matthew and Bruinsma, Wessel and Tobaben, Marlon and Honkela, Antti and Turner, Richard},
title = {Noise-Aware Differentially Private Regression via Meta-Learning},
booktitle = {NeurIPS 2024},
year = {2024},
month = {June},
abstract = {Many high-stakes applications require machine learning models that protect user privacy and provide well-calibrated, accurate predictions. While Differential Privacy (DP) is the gold standard for protecting user privacy, standard DP mechanisms typically significantly impair performance. One approach to mitigating this issue is pre-training models on simulated data before DP learning on the private data. In this work we go a step further, using simulated data to train a meta-learning model that combines the Convolutional Conditional Neural Process (ConvCNP) with an improved functional DP mechanism of Hall et al. [2013] yielding the DPConvCNP. DPConvCNP learns from simulated data how to map private data to a DP predictive model in one forward pass, and then provides accurate, well-calibrated predictions. We compare DPConvCNP with a DP Gaussian Process (GP) baseline with carefully tuned hyperparameters. The DPConvCNP outperforms the GP baseline, especially on non-Gaussian data, yet is much faster at test time and requires less tuning.},
url = {http://approjects.co.za/?big=en-us/research/publication/noise-aware-differentially-private-regression-via-meta-learning/},
}