thecml/dpsgd-optimizer thecml/dpsgd-optimizer

  • Stars
    star
    40
  • Rank 680,660 (Top 14 %)
  • Language
    Python
  • License
    MIT License
  • Created about 4 years ago
  • Updated 7 months ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
thecml/dpsgd-optimizer
github

thecml

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Amortized version of the differentially private SGD algorithm published in "Deep Learning with Differential Privacy" by Abadi et al. Enforces privacy by clipping and sanitising the gradients with Gaussian noise during training.

More Repositories

1

pytorch-lmdb

A simple Lightning Memory-Mapped Database (LMDB) converter for ImageFolder datasets in PyTorch. Using LMDB over a regular file structure improves I/O performance significantly. Works on both Windows and Linux. Comes with latest Python support.
Python
16
star
2

thesis-cloudksvd

Master's thesis about sparse approximation and dictionary learning using Cloud K-SVD for image denoising. Results show that the algorithm is able to learn sparse representations of signal vectors from distributed data samples in a heterogeneous network setup.
Python
6
star
3

ball-bearing-survival

Implementation of Predicting Survival Time of Ball Bearings in the Presence of Censoring (AAAI Fall Symposium 2023)
Python
3
star
4

rulsurv

Code for: A probabilistic estimation of remaining useful life from censored time-to-event data (2024)
Python
3
star
5

lego-keras-gan

A GAN to create images of LEGO figures.
Python
2
star
6

ertms-modelling-vdm

An Overture project that models ERTMS level 2 and interlocking properties in VDM++.
TeX
2
star
7

UE-BNNSurv

Official TensorFlow implementation of Uncertainty Estimation in Deep Bayesian Survival Models (BHI 2023)
Jupyter Notebook
2
star
8

mensa

MENSA: A Multi-Event Network for Survival Analysis under Informative Censoring (2024)
Python
2
star
9

kubernetes-exercises

Hands-on exercises for Docker and Kubernetes.
TeX
1
star
10

survival-datasets

Data loader for most common datasets in survival analysis.
Python
1
star
11

fedasync-with-fairness

FedAsync with proposed fairness improvements
Python
1
star
12

baysurv-wip

Jupyter Notebook
1
star
13

cloud-ksvd

Cloud K-SVD for Image Denoising
Python
1
star
14

neural_embedder

A small library that can encode categorical variables to entity embeddings using a TensorFlow 2.0 neural network. Supports classification and regression problems. Network parameters are adjustable.
Python
1
star
15

csgo-ai-challenge

Skybox presented an AI challenge that ran from Spring to Fall 2020, where teams had to predict the winner of rounds in the tactical shooter CS:GO. This project uses TensorFlow, Scikit-learn and CatBoost to train robust model ensembles using the most relevant features.
Python
1
star