Bounding the Excess Risk for Linear Models Trained on Marginal-Preserving, Differentially-Private, Synthetic Data

no code implementations • 6 Feb 2024 • Yvonne Zhou, Mingyu Liang, Ivan Brugere, Dana Dachman-Soled, Danial Dervovic, Antigoni Polychroniadou, Min Wu

The growing use of machine learning (ML) has raised concerns that an ML model may reveal private information about an individual who has contributed to the training dataset.

MetaDIP: Accelerating Deep Image Prior with Meta Learning

no code implementations • 18 Sep 2022 • Kevin Zhang, Mingyang Xie, Maharshi Gor, Yi-Ting Chen, Yvonne Zhou, Christopher A. Metzler

Deep image prior (DIP) is a recently proposed technique for solving imaging inverse problems by fitting the reconstructed images to the output of an untrained convolutional neural network.

Denoising Meta-Learning +1