Qingsong Wang
I am currently a Postdoc in the Halıcıoğlu Data Science Institute at UCSD, and my postdoc mentors are Prof. Mikhail Belkin and Prof. Yusu Wang. Previously, I was a postdoc in the Mathematics department of the University of Utah. I received my Ph.D. in math from The Ohio State University under the supervision of Prof. Facundo Mémoli. In the early years of my Ph.D., I studied complex geometry under the supervision of Prof. Fangyang Zheng.
Email: qiw072 at ucsd dot edu
Research Interests:
Applied Algebraic Topology
Machine Learning
Metric Geometry
Differential Geometry
Publications:
2024
"Monotone Operator Theory-Inspired Message Passing for Learning Long-Range Interaction on Graphs" Justin Baker*, Qingsong Wang*, Martin Berzins, Thomas Strohmer, Bao Wang [International Conference on Artificial Intelligence and Statistics (AISTAT 2024)]
"Measure Theoretic Reeb Graphs and Reeb Spaces" Qingsong Wang, Guanquan Ma, Raghavendra Sridharamurthy, Bei Wang [Symposium on Computational Geometry (SoCG 2024)]
2023
"Implicit Graph Neural Networks: A Monotone Operator Viewpoint" Justin Baker*, Qingsong Wang*, Cory D Hauck, and Bao Wang, [International Conference on Machine Learning (ICML 2023).]
“Momentum Ensures Convergence of SIGNSGD under Weaker Assumptions” Tao Sun*, Qingsong Wang*, Dongsheng Li, and Bao Wang, [International Conference on Machine Learning (ICML 2023).]
2022
"The Persistent Topology of Optimal Transport Based Metric Thickenings." Henry Adams, Facundo Mémoli, Michael Moy, and Qingsong Wang, [Algebraic & Geometric Topology. arXiv:2109.15061 ].
2021
"Manifolds with Positive Orthogonal Ricci Curvature." Lei Ni, Qingsong Wang, and Fangyang Zheng, [American Journal of Mathematics 143.3 (2021): 833-857. arXiv:1806.10233]
2020
"On Bismut Flat Manifolds." Qingsong Wang, Bo Yang, and Fangyang Zheng, Transactions of the American Mathematical Society 373 (8), 5747-5772 (2020) [https://arXivorg/abs/1603.07058 ]
Preprints:
2023
"It begins with a boundary: A geometric view on probabilistically robust learning" Leon Bungert, Nicolás García Trillos, Matt Jacobs, Daniel McKenzie, Đorđe Nikolić, Qingsong Wang, arXiv preprint arXiv:2305.18779
"Extremal spherical polytopes and Borsuk's conjecture" Mikhail Katz, Facundo Mémoli, and Qingsong Wang [arXiv.:2301.13076, (2023)]
2022
"Gromov-Hausdorff distances, Borsuk-Ulam theorems, and Vietoris-Rips complexes." With Henry Adams, Johnathan Bush, Nate Clause, Florian Frick, Mario Gómez, Michael Harrison, R. Amzi Jeffs, Evgeniya Lagoda, Sunhyuk Lim, Facundo Mémoli, Michael Moy, Nikola Sadovek, Matt Superdock, Daniel Vargas, Qingsong Wang, and Ling Zhou. [arXiv: 2301.00246, (2022)].
2021
"Some results about the Tight Span of spheres." with Sunhyuk Lim, Facundo Mémoli, Zhengchao Wan, Qingsong Wang, and Ling Zhou.[arXiv:2112.12646 (2021)]
"Metric Graph Approximations of Geodesic Spaces." with Facundo Mémoli, Osman Okutan, and Qingsong Wang [arXiv:1809.05566 (2021)].
Services:
- Review:
Journals: "Annali della Scuola Normale Superiore di Pisa," "Journal of Applied and Computational Topology," "Journal of Approximation Theory," and "Neurocomputing." "Foundations of Data Science"
Conferences: "Symposium on Computational Geometry" 2020, 2022, and 2023, "TAG for Pattern Recognition with Applications" (CVPR 23, workshop), "TAG for Machine Learning" (ICML 23, workshop), NeurIPS 2023, ICLR 2024, ICML 2024.
- Mentoring:
Directed Reading Program at OSU (Spring 2022)
Mentee: Harrison Blake
Project: “On the Poincaré-Hopf Theorem”
- Others:
Assistant of 2022 MRC Summer Conferences on "Data Science at the Crossroads of Analysis, Geometry, and Topology"
Mini-symposium Organizer of 2nd SIAM Northern States Section Conference at Logan, Utah