Persistence in PyTorch

Primoz Skraba writes:
Announcing a persistent homology layer for PyTorch. The layer takes in either a simplicial complex or a point cloud, computes the persistence diagram and given an energy function automatically backpropogates. This allows for simple integration with other PyTorch modules as well as continuous optimization over persistence diagrams. Our goal is to make experimentation combining topology and deep networks easier and more accessible.

The module along with installation instructions and several examples can be found at

The companion paper describing the examples can be found at

2019 Union College Mathematics Conference


Schenectady, New York

September 13-15, 2019

This year, the conference topics are applied topology; differential geometry, geometric analysis, and mathematical physics; number theory; and the history of mathematics. The plenary speakers of the conference are:

Justin Curry, Michael Lesnick, and I are co-organizing the special session on applied topology. We would like to encourage you to submit an abstract for a 20 minute talk in this special session.  We hope to have 10-12 speakers in total. The deadline for abstract submissions is July 19, 2019.For more information about the conference and to register, please visit our website at:

We hope to see you in Schenectady in September!

On behalf of the organizers,

Ellen Gasparovic