6th Workshop on Geometry and Machine Learning
Friday June 10, 2022 | 14:30 - 18:00 | Berlin, Germany (with remote option)
Talks will be in person or hybrid (). Hybrid attendance through CG week registration.
Organized by Hu Ding, Mustafa Hajij, and Jeff M. Phillips.
Machine learning (broadly defined) concerns techniques that can learn from and make predictions on data. Such algorithms are built to explore the useful pattern of the input data, which usually can be stated in terms of geometry (e.g., problems in high dimensional feature space). Hence computational geometry plays a crucial and natural role in machine learning. Importantly, geometric algorithms often come with quality guaranteed solutions when dealing with high-dimensional data. The computational geometry community has many researchers with the unique knowledge on high dimensional geometry, which could be utilized to have a great impact on machine learning or any data related fields.

This workshop is intended to provide a forum for those working in the fields of computational geometry, machine learning and the various theoretical and algorithmic challenges to promote their interaction and blending. To this end, the workshop will consist of an invited talks and several contributed talks. The invited talk will mainly serve as tutorials about the applications of geometric algorithms in machine learning. Such interaction will stimulate those working in both fields, and we can expect that a synergy can promote many new interesting geometric problems, concepts and ideas, which will contribute to open up new vistas in computational geometry communities.

This workshop is being held as part of CG Week 2022 (June 7-10, 2022 in Berlin, Germany) which also includes the International Symposium on Computational Geometry (SoCG).

(all times may change subject to conference schedule)
Contributed Talks
14:30-14:50 Leyla Biabani (TU/Eindhoven) Coresets for the k-Center Problem with Outliers
with Mark de Berg and Morteza Monemizadeh
14:50-15:10 Iordan Ganev (Radboud University) The QR Decomposition for Radial Neural Networks
with Twan van Laarhoven and Robin Walters
15:10-15:30 Jules Wulms (Technische Universitat Wien) The Influence of Dimensions on the Complexity of Computing Decision Trees
with Stephen Kobourov, Maarten Loffler, Fabrizio Montecchiani, Marcin Pilipczuk, Ignaz Rutter, Raimund Seidel, and Manuel Sorge
Coffee Break
Invited Talk
16:00 - 17:00 Michael Schaub (RWTH Aachen University) Signal Processing on Graphs and Complexes
Dr. Michael Schaub studied Electrical Engineering and Information Technology at ETH Zurich. After an MSc in Biomedical Engineering at Imperial College London, he obtained his PhD in Mathematics at Imperial College London in 2014. In the following he worked as a Research Fellow in Belgium, jointly at the Universite catholique de Louvain and at the University of Namur. In November 2016, Dr. Schaub moved to the Massachusetts Institute of Technology (MIT) as a Postdoctoral Research Associate. From July 2017 onwards he was a Marie Sklodowska Curie Fellow at MIT and the University of Oxford, before joining RWTH Aachen University in June 2020, supported by the NRW Return Programme (2019). He was awarded an ERC Starting grant in 2022. Graph signal processing (GSP) tries to device appropriate tools to process signals supported on graphs by generalizing classical methods from signal processing of time-series and images - such as smoothing, filtering and interpolation - to signals supported on the nodes of a graph. Typically, this involves leveraging the structure of the graph as encoded in the spectral properties of the graph Laplacian. In certain scenarios, such as traffic network analysis, the signals of interest are however naturally defined as flows the edges of a graph, rather than on the nodes. After a brief recap of the central ideas of GSP, we examine why standard tools from GSP may not be suitable for the analysis of such flow signals. More specifically, we discuss how the underlying notion of 'signal vs noise' inherited from typically considered variants of the graph Laplacian are not suitable when dealing with edge signals that encode flows. To overcome this limitation, we devise signal processing tools based on the Hodge-Laplacian and the associated discrete Hodge Theory for simplicial (and cellular) complexes. We discuss applications of these ideas for signal smoothing, semi-supervised and active learning for edge-flows on discrete or discretized spaces.
Contributed Talks
17:00-17:20 Louis Theran (University of St Andrews) Maximum Likelihood Thresholds via Graph Rigidity
with Daniel Irving Bernstein, Sean Dewar, Steven J. Gortler, Anthony Nixon, and Meera Sitharam
17:20-17:40 Chao Chen (Stoney Brook University) Persistent Homology for Trojan Detection
with Songzhu Zheng, Yikai Zhang, Hubert Wagner, and Mayank Goswami
17:40-18:00 Elizabeth Coda (Pacific Northwest National Lab) Fiber Bundle Morphisms as a Framework for Modeling Many-to-Many Maps
with Nico Courts, Colby Wight, Loc Truong, WoongJo Choi, Charles Godfrey, Tegan Emerson, Keerti Kappagantula, and Henry Kvinge

Contributed Talks: To submit a contributed talk to be considered for a presentation, send an email to WoGeomML@gmail.com with an abstract (e.g., 2 pages) or preferably link to permanent, publically available version (e.g., at arXiv.org). The email should contain a list of authors, and should identify the name of the person presenting. Indicate if you hope to attend in person, or will prefer a virtual option.
We received contributions until May 15, 2022.
Generous support provided by NSF CCF-2115677.
The previous versions of this workshop were:
  • Workshop on Geometry and Machine Learning
  • 2nd Workshop on Geometry and Machine Learning
  • 3rd Workshop on Geometry and Machine Learning
  • 4th Workshop on Geometry and Machine Learning
  • 5th Workshop on Geometry and Machine Learning