Peter Macgregor

Summary

I'm a Research Associate in the Laboratory for the Foundations of Computer Science (LFCS), School of Informatics at the University of Edinburgh. My research interests are in unsupervised learning and algorithmic spectral graph theory.

I like to take ideas from theoretical computer science and demonstrate their applicability. To this end, I am developing an open-source library of efficient spectral graph algorithms along with He Sun.

Publications

ICML 2022

A Tighter Analysis of Spectral Clustering, and Beyond

Peter Macgregor and He Sun

arXiv version conference version talk code

@inproceedings{macgregorTighterAnalysisSpectral2022,
    title = {A Tighter Analysis of Spectral Clustering, and Beyond},
    booktitle = {39th {{International Conference}} on {{Machine Learning}} ({{ICML}}'22)},
    author = {Macgregor, Peter and Sun, He},
    year = {2022},
    pages = {14717--14742}
}

NeurIPS 2021

Finding Bipartite Components in Hypergraphs

Peter Macgregor and He Sun

arXiv version conference version talk code

@inproceedings{macgregorFindingBipartiteComponents2021,
    title = {Finding Bipartite Components in Hypergraphs},
    booktitle = {34th {{Advances}} in {{Neural Information Processing Systems}} ({{NeurIPS}}'21)},
    author = {Macgregor, Peter and Sun, He},
    year = {2021},
    pages = {7912--7923}
}

ICML 2021 Oral

Local Algorithms for Finding Densely Connected Clusters

Peter Macgregor and He Sun

arXiv version conference version talk code demo

@inproceedings{macgregorLocalAlgorithmsFinding2021,
  title = {Local Algorithms for Finding Densely Connected Clusters},
  booktitle = {38th {{International Conference}} on {{Machine Learning}} ({{ICML}}'21)},
  author = {Macgregor, Peter and Sun, He},
  year = {2021},
  pages = {7268--7278}
}

Preprints

arXiv version

Is the Algorithmic Kadison-Singer Problem Hard?

Ben Jourdan, Peter Macgregor, and He Sun

@article{jourdanAlgorithmicKadisonSinger2022,
    author     = {Ben Jourdan and Peter Macgregor and He Sun},
    title      = {Is the Algorithmic Kadison-Singer Problem Hard?},
    journal    = {CoRR},
    volume     = {abs/2205.02161},
    year       = {2022},
    doi        = {10.48550/arXiv.2205.02161},
    eprinttype = {arXiv},
    eprint     = {2205.02161}
}

Thesis

arXiv version

On Learning the Structure of Clusters in Graphs

Peter Macgregor, PhD Thesis, University of Edinburgh, 2022

@phdthesis{macgregorLearningStructureClusters2022,
    title = {On Learning the Structure of Clusters in Graphs},
    author = {Macgregor, Peter},
    year = {2022},
    school = {University of Edinburgh}
}

Peter Macgregor

Summary

Publications

ICML 2022

A Tighter Analysis of Spectral Clustering, and Beyond

NeurIPS 2021

Finding Bipartite Components in Hypergraphs

ICML 2021 Oral

Local Algorithms for Finding Densely Connected Clusters

Preprints

arXiv version

Is the Algorithmic Kadison-Singer Problem Hard?

Thesis

arXiv version

On Learning the Structure of Clusters in Graphs

Talks

Edinburgh LFCS 2022

MathWorks 2022

Beyond Symmetric Clusters: Finding Inter-Cluster Structure in Graphs