Skip to content
conftrace_

private training

10 papers

Explore in graph

Co-occurring keywords · papers mentioning both

differential privacy (9) gradient clipping (3) public pretraining (2) distribution shift (2) deep learning (2) transfer learning (2) stochastic gradient descent (2) model compression (2) public representation (1) privacy amplification (1)

Papers

Cocoon: A System Architecture for Differentially Private Training with Correlated Noises OSDI 2026 All Rivers Run to the Sea: Private Learning with Asymmetric Flows CVPR 2024 DP-SGD Without Clipping: The Lipschitz Neural Network Way ICLR 2024 HEPrune: Fast Private Training of Deep Neural Networks With Encrypted Data Pruning NeurIPS 2024 On the Benefits of Public Representations for Private Transfer Learning under Distribution Shift NeurIPS 2024 (Amplified) Banded Matrix Factorization: A unified approach to private training NeurIPS 2023 Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger NeurIPS 2023 Why Is Public Pretraining Necessary for Private Model Training? ICML 2023 Scalable and Efficient Training of Large Convolutional Neural Networks with Differential Privacy NeurIPS 2022 Fast and Memory Efficient Differentially Private-SGD via JL Projections NeurIPS 2021