5th Workshop on Geometry and Machine Learning
Tuesday June 8, 2021 | 1:20 - 4:30pm EDT | Buffalo, NY, USA (Online)
Organized by Hu Ding and Jeff 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 2021 (June 7-11, 2021 in Buffalo, NY, USA) which also includes the International Symposium on Computational Geometry (SoCG). All times are EDT.

Invited Talk
1:20 - 2:00 Rong Ge (Duke University) Geometry and Landscape for Nonconvex Functions
Rong Ge is an assistant professor at Duke University. He received his Ph.D. from Princeton University, advised by Sanjeev Arora. Before joining Duke Rong Ge was a post-doc at Microsoft Research New England. Rong Ge's research focuses on proving theoretical guarantees for modern machine learning algorithms, and understanding the optimization for non-convex optimization and in particular neural networks. Rong Ge has received NSF CAREER award and Sloan Fellowship. Nonconvex optimization is a popular approach in machine learning. In the recent years, a lot of progress on nonconvex optimization relied on geometric properties for the landscape of nonconvex objective functions. In this talk we will briefly survey some geometry properties that are known to make nonconvex optimization easy, as well as some geometric properties for the landscape of overparametrized deep neural networks that we don't fully understand.
Contributed Talks
2:05-2:18 Siddharth Barman, Ramakrishnan Krishnamurthy, Saladi Rahul (Indian Institute of Science) Optimal Algorithms for Range Searching over Multi-Armed Bandits
2:20-2:33 Michael Joswig, Marek Kaluba (Karlsruher Institute fur Technologie), Lukas Ruff Geometric Disentanglement by Random Convex Polytopes
2:35-2:48 Pantea Haghighatkhah, Wouter Meulemans, Bettina Speckmann, Jerome Urhausen, Kevin Verbeek (Utrecht University) Obstructing Classification Via Projection
Coffee Break
3:00-3:13 Rolando Kindelan, Jose Frias, Mauricio Cerda, Nancy Hitschfeld (University of Chile) Classification based on Topological Data Analysis
3:15-3:28 Henry Kvinge, Zachary New, Nico Courts, Jung H. Lee, Lauren A. Phillips, Courtney D. Corley, Aaron Tuor, Andrew Avila, Nathan O. Hodas (U Washington & PNNL) Fuzzy Simplicial Networks: A Topology-Inspired Model to Improve Task Generalization in Few-shot Learning
3:30-3:43 Mustafa Hajij, Kyle Istvan, Ghada Zamzmi (Santa Clara University) Geometric Message Passing Schemes with Cell Complex Neural Networks
3:45-3:58 Mikkel Abrahamsen, Linda Kleist, and Tillmann Miltzow (Utrecht University) Training Neural Networks is ER-complete
4:00-4:13 Apostolos Chalkis, Vissarion Fisikopoulos (Oracle), Marios Papachristou, Elias Tsigaridas Truncated Log-concave Sampling with Reflective Hamiltonian Monte Carlo
4:15-4:28 Alejandro Flores-Velazco and David M. Mount (U Maryland) Boundary-Sensitive Approach for Approximate Nearest-Neighbor Classification



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 link to permanent, publically available version (e.g., at arXiv.org). The email should contain a list of authors and the name of the person presenting.
We received contributions until April 30, 2021. Submissions are now closed.


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