Search Results for author: Pranav Subramani

Found 2 papers, 2 papers with code

Enabling Fast Differentially Private SGD via Just-in-Time Compilation and Vectorization

1 code implementation NeurIPS 2021 Pranav Subramani, Nicholas Vadivelu, Gautam Kamath

We also rebuild core parts of TensorFlow Privacy, integrating features from TensorFlow 2 as well as XLA compilation, granting significant memory and runtime improvements over the current release version.

SPFlow: An Easy and Extensible Library for Deep Probabilistic Learning using Sum-Product Networks

1 code implementation11 Jan 2019 Alejandro Molina, Antonio Vergari, Karl Stelzner, Robert Peharz, Pranav Subramani, Nicola Di Mauro, Pascal Poupart, Kristian Kersting

We introduce SPFlow, an open-source Python library providing a simple interface to inference, learning and manipulation routines for deep and tractable probabilistic models called Sum-Product Networks (SPNs).

Cannot find the paper you are looking for? You can Submit a new open access paper.