# D3p -- A Python Package for Differentially-Private Probabilistic Programming

arXiv: https://arxiv.org/abs/2103.11648 · HTML: https://mlsanity.com/paper/2103.11648/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 55 references that are in the map.
- First posted on arXiv 22 Mar 2021.

## Builds on (most cited first, 17 of 17)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Pyro: Deep Universal Probabilistic Programming](https://mlsanity.com/paper/1810.09538/) (2018)
- [Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyro](https://mlsanity.com/paper/1912.11554/) (2019)
- [The Discrete Gaussian for Differential Privacy](https://mlsanity.com/paper/2004.00010/) (2020)
- [The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation](https://mlsanity.com/paper/2102.06387/) (2021)
- [Theano: A Python framework for fast computation of mathematical expressions](https://mlsanity.com/paper/1605.02688/) (2016)
- [Enabling Fast Differentially Private SGD via Just-in-Time Compilation and Vectorization](https://mlsanity.com/paper/2010.09063/) (2020)
- [Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT](https://mlsanity.com/paper/2006.07134/) (2020)
- [Simple, Distributed, and Accelerated Probabilistic Programming](https://mlsanity.com/paper/1811.02091/) (2018)
- [Differentially Private Variational Inference for Non-conjugate Models](https://mlsanity.com/paper/1610.08749/) (2016)
- [That which we call private](https://mlsanity.com/paper/1908.03566/) (2019)
- [Privacy-preserving data sharing via probabilistic modelling](https://mlsanity.com/paper/1912.04439/) (2019)
- [Randomness Concerns When Deploying Differential Privacy](https://mlsanity.com/paper/2009.03777/) (2020)
- [Preserving differential privacy under finite-precision semantics](https://mlsanity.com/paper/1306.2691/) (2013)

## Built on by (most cited first, 2 of 2)

- [DPVIm: Differentially Private Variational Inference Improved](https://mlsanity.com/paper/2210.15961/) (2022)
- [Privacy-Preserving Taxi-Demand Prediction Using Federated Learning](https://mlsanity.com/paper/2305.08107/) (2023)

## Abstract (arXiv)

We present d3p, a software package designed to help fielding runtime efficient widely-applicable Bayesian inference under differential privacy guarantees. d3p achieves general applicability to a wide range of probabilistic modelling problems by implementing the differentially private variational inference algorithm, allowing users to fit any parametric probabilistic model with a differentiable density function. d3p adopts the probabilistic programming paradigm as a powerful way for the user to flexibly define such models. We demonstrate the use of our software on a hierarchical logistic regression example, showing the expressiveness of the modelling approach as well as the ease of running the parameter inference. We also perform an empirical evaluation of the runtime of the private inference on a complex model and find a ~10 fold speed-up compared to an implementation using TensorFlow Privacy.