TheSalon / fast-dpsgdLinks
Code for fast dpsgd implementations in JAX/TF
☆59Updated 2 years ago
Alternatives and similar repositories for fast-dpsgd
Users that are interested in fast-dpsgd are comparing it to the libraries listed below
Sorting:
- Github pages backend for https://differentialprivacy.org☆26Updated 2 weeks ago
- Algorithms for Privacy-Preserving Machine Learning in JAX☆95Updated this week
- ☆37Updated 3 years ago
- [NeurIPS 2020] Simple and practical private mean and covariance estimation.☆35Updated 4 years ago
- Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture"☆105Updated 4 years ago
- Randomized Smoothing of All Shapes and Sizes (ICML 2020).☆52Updated 4 years ago
- Pytorch optimizers implementing Hilbert Constrained Gradient Descent☆19Updated 6 years ago
- Hessian spectral density estimation in TF and Jax☆123Updated 4 years ago
- Federated posterior averaging implemented in JAX☆51Updated 2 years ago
- Convolutional Neural Tangent Kernel☆111Updated 5 years ago
- Computationally friendly hyper-parameter search with DP-SGD☆26Updated 6 months ago
- The Full Spectrum of Deepnet Hessians at Scale: Dynamics with SGD Training and Sample Size☆17Updated 6 years ago
- Learning perturbation sets for robust machine learning☆65Updated 3 years ago
- Neural network verification in JAX☆145Updated last year
- This repo contains the underlying code for all the experiments from the paper: "Automatic Discovery of Privacy-Utility Pareto Fronts"☆27Updated 2 years ago
- Tilted Empirical Risk Minimization (ICLR '21)☆59Updated last year
- ☆157Updated 3 years ago
- A concise primer on Differential Privacy☆29Updated 5 years ago
- Geometric Certifications of Neural Nets☆42Updated 2 years ago
- ☆123Updated last year
- ☆62Updated 4 years ago
- 🧀 Pytorch code for the Fromage optimiser.☆125Updated last year
- This code reproduces the results of the paper, "Measuring Data Leakage in Machine-Learning Models with Fisher Information"☆50Updated 3 years ago
- ☆80Updated 3 years ago
- CIFAR-5m dataset☆39Updated 4 years ago
- FedJAX is a JAX-based open source library for Federated Learning simulations that emphasizes ease-of-use in research.☆265Updated last month
- InstaHide: Instance-hiding Schemes for Private Distributed Learning☆50Updated 4 years ago
- CHOP: An optimization library based on PyTorch, with applications to adversarial examples and structured neural network training.☆77Updated last year
- Privacy-Preserving Bandits (MLSys'20)☆22Updated 2 years ago
- ☆133Updated 4 years ago