Quantized Gromov-Wasserstein

1 code implementation • 5 Apr 2021 • 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.

Quantization

Generalized Spectral Clustering via Gromov-Wasserstein Learning

1 code implementation • 7 Jun 2020 • Samir Chowdhury, Tom Needham

A key insight of the GWL framework toward graph partitioning was to compute GW correspondences from a source graph to a template graph with isolated, self-connected nodes.

Clustering graph partitioning +1

Path homologies of deep feedforward networks

no code implementations • 16 Oct 2019 • Samir Chowdhury, Thomas Gebhart, Steve Huntsman, Matvey Yutin

These results provide a foundation for investigating homological differences between neural network architectures and their realized structure as implied by their parameters.

Gromov-Wasserstein Averaging in a Riemannian Framework

1 code implementation • 10 Oct 2019 • 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 asymmetric) matrices with arbitrary entries and sizes.

The Gromov-Wasserstein distance between networks and stable network invariants

1 code implementation • 13 Aug 2018 • Samir Chowdhury, Facundo Mémoli

We define a metric---the Network Gromov-Wasserstein distance---on weighted, directed networks that is sensitive to the presence of outliers.

Discrete Mathematics Metric Geometry

Improved Error Bounds for Tree Representations of Metric Spaces

no code implementations • NeurIPS 2016 • Samir Chowdhury, Facundo Mémoli, Zane T. Smith

We consider an embedding of a metric space into a tree proposed by Gromov.

Clustering