Not all noise is accounted equally: How differentially private learning
benefits from large sampling rates
International Workshop on Machine Learning for Signal Processing (MLSP), 2021
Papers citing "Not all noise is accounted equally: How differentially private learning benefits from large sampling rates"
18 / 18 papers shown
Title |
|---|
 R+R:Understanding Hyperparameter Effects in DP-SGDAsia-Pacific Computer Systems Architecture Conference (ACSA), 2024 |
 Nearly Tight Black-Box Auditing of Differentially Private Machine
LearningNeural Information Processing Systems (NeurIPS), 2024 |
 Sparsity-Preserving Differentially Private Training of Large Embedding
ModelsNeural Information Processing Systems (NeurIPS), 2023 |
 Differentially Private Video Activity RecognitionIEEE Workshop/Winter Conference on Applications of Computer Vision (WACV), 2023 |
 Differentially Private Image Classification by Learning Priors from
Random ProcessesNeural Information Processing Systems (NeurIPS), 2023 |
