twistedcubic / coin-press
[NeurIPS 2020] Simple and practical private mean and covariance estimation.
☆34Updated 4 years ago
Alternatives and similar repositories for coin-press:
Users that are interested in coin-press are comparing it to the libraries listed below
- Github pages backend for https://differentialprivacy.org☆25Updated 7 months ago
- ☆80Updated 2 years ago
- Computationally friendly hyper-parameter search with DP-SGD☆23Updated last week
- ☆27Updated 2 years ago
- ☆22Updated 2 years ago
- Code for fast dpsgd implementations in JAX/TF☆58Updated 2 years ago
- Code for Auditing DPSGD☆38Updated 2 years ago
- ☆8Updated 7 years ago
- Randomized Smoothing of All Shapes and Sizes (ICML 2020).☆52Updated 4 years ago
- Federated posterior averaging implemented in JAX☆51Updated last year
- Hadamard Response: Communication efficient, sample optimal, linear time locally private learning of distributions☆14Updated 4 years ago
- Code for Canonne-Kamath-Steinke paper https://arxiv.org/abs/2004.00010☆59Updated 4 years ago
- ☆17Updated 2 years ago
- Code for "Differential Privacy Has Disparate Impact on Model Accuracy" NeurIPS'19☆35Updated 3 years ago
- Code for the CSF 2018 paper "Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting"☆38Updated 5 years ago
- Algorithms for Privacy-Preserving Machine Learning in JAX☆91Updated 7 months ago
- ☆10Updated 2 years ago
- The Full Spectrum of Deepnet Hessians at Scale: Dynamics with SGD Training and Sample Size☆17Updated 5 years ago
- ☆13Updated last year
- ☆38Updated 3 years ago
- Code to reproduce experiments in "Antipodes of Label Differential Privacy PATE and ALIBI"☆30Updated 2 years ago
- Differentially Private Conditional Generative Adversarial Network☆30Updated 3 years ago
- Research and experimental code related to Opacus, an open-source library for training PyTorch models with Differential Privacy☆17Updated 3 months ago
- Official implementation for Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds (NeurIPS, 2021).☆22Updated 2 years ago
- ☆10Updated last year
- Differentially Private Generative Adversarial Networks for Time Series, Continuous, and Discrete Open Data☆33Updated 6 years ago
- [ICML'20] Multi Steepest Descent (MSD) for robustness against the union of multiple perturbation models.☆26Updated 5 months ago
- A fast algorithm to optimally compose privacy guarantees of differentially private (DP) mechanisms to arbitrary accuracy.☆73Updated 11 months ago
- Analytic calibration for differential privacy with Gaussian perturbations☆46Updated 6 years ago
- Federated Principal Component Analysis Revisited!☆39Updated 3 years ago