activity
20172021
most citedPath homologies of deep feedforward networks

15 citations · 16 across the 3 of their papers we have counts for

collaborators

8 papers

cs.LG2021

Quantized Gromov-Wasserstein

Samir Chowdhury, David Miller, Tom Needham

The Gromov-Wasserstein (GW) framework adapts ideas from optimal transport to allow for the comparison of probability distributions defined on different metric spaces. Scalable comp…

cs.SI2020

Path homology and temporal networks

Samir Chowdhury, Steve Huntsman, Matvey Yutin

We present an algorithm to compute path homology for simple digraphs, and use it to topologically analyze various small digraphs en route to an analysis of complex temporal network…

cs.LG2020

Generalized Spectral Clustering via Gromov-Wasserstein Learning

Samir Chowdhury, Tom Needham

We establish a bridge between spectral clustering and Gromov-Wasserstein Learning (GWL), a recent optimal transport-based approach to graph partitioning. This connection both expla…

math.AT201915 cited

Path homologies of deep feedforward networks

Samir Chowdhury, Thomas Gebhart, Steve Huntsman +1

We provide a characterization of two types of directed homology for fully-connected, feedforward neural network architectures. These exact characterizations of the directed homolog…

math.MG2019

Gromov-Wasserstein Averaging in a Riemannian Framework

Samir Chowdhury, Tom Needham

We introduce a theoretical framework for performing statistical tasks---including, but not limited to, averaging and principal component analysis---on the space of (possibly asymme…

math.MG20191 cited

Geodesics in persistence diagram space

Samir Chowdhury

It is known that for a variety of choices of metrics, including the standard bottleneck distance, the space of persistence diagrams admits geodesics. Typically these existence resu…