Pre-trained perceptual features improve differentially private image generation

F Harder, MJ Asadabadi, DJ Sutherland… - arXiv preprint arXiv …, 2022 - arxiv.org
Training even moderately-sized generative models with differentially-private stochastic
gradient descent (DP-SGD) is difficult: the required level of noise for reasonable levels of …
被引用次数：17 相关文章

Pre-trained Perceptual Features Improve Differentially Private Image Generation

F Harder, M Jalali, DJ Sutherland, M Park - Transactions on Machine … - openreview.net
Training even moderately-sized generative models with differentially-private stochastic
gradient descent (DP-SGD) is difficult: the required level of noise for reasonable levels of …

Pre-trained Perceptual Features Improve Differentially Private Image Generation

F Harder, M Jalali Asadabadi, DJ Sutherland… - arXiv e …, 2022 - ui.adsabs.harvard.edu
Training even moderately-sized generative models with differentially-private stochastic
gradient descent (DP-SGD) is difficult: the required level of noise for reasonable levels of …