An algorithm for private density estimation.
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Failed to load latest commit information.

Private Density Estimation

This package contains the algorithm and experiments for the following paper:

Differentially Private Learning of Structured Discrete Distributions
Ilias Diakonikolas, Moritz Hardt, Ludwig Schmidt
NIPS 2015

The code is written in Julia (v0.5). The script src/histogram_experiment.jl runs the experiments in the paper for synthetic distributions (mixtures of Gaussian, Beta, and Gamma distributions).

For an example of how to use the code, see the Jupyter notebook examples/histogram_approximation.ipynb.

The three plots above are generated in the notebook examples/website_plots.ipynb.