We are thrilled to announce the first official TAG-DS Stand-Alone Event-- TAG... We're it! This will be a two day event, December 1 & 2, 2025, featuring keynotes, poster sessions, spotlight talks, collaboration activities, and community development. The dates and location were selected to align with NeurIPS 2025-- twice the fun! The event will be hosted on the University of California San Diego campus both days and is readily accessible by public transit from downtown for those already planning to attend NeurIPS. There will be an associated Proceedings of Machine Learning Research volume for papers submitted to the archival track.
Important Dates and Information
Day of Information
Location: The Conference the conference will be held in the East Ballroom, 2nd Floor, UCSD's Price Center
Location Parking: For those driving, 8th College/Theater District Parking has 24hr parking
Pre-conference Information
Paper and Abstract Submission Deadline: Extended to October 8, 2025 (AOE) October 1, 2025 (AOE)
Register HERE! Participation will be capped at 200 for the first year-- don't wait, register now!
Author Notification Date: November 12, 2025 (AOE)
Camera Ready Papers Due: November 24, 2025 (AOE)
Become a Reviewer here!
Download the call for papers and share with your network!
Keynotes
Dr. Richard Baraniuk
Richard G. Baraniuk is the C. Sidney Burrus Professor of Electrical and Computer Engineering at Rice University, a member of the Digital Signal Processing (DSP) research group, a member of the Ken Kennedy Institute, the Founder/Director of OpenStax, and the Principal Investigator and Director of SafeInsights, NSF's national research infrastructure for learning and education. He is also a joint faculty member in the Rice departments of Computer Science and Statistics.
Dr. Baraniuk is a member of the US National Academy of Engineering and American Academy of Arts and Sciences and a fellow of the National Academy of Inventors, American Association for the Advancement of Science, and IEEE. He has received the DOD Vannevar Bush Faculty Fellow Award (National Security Science and Engineering Faculty Fellowship), the IEEE Jack S. Kilby Signal Processing Medal, the IEEE Signal Processing Society Norbert Wiener Society Award and Claude Shannon-Harry Nyquist Technical Achievement Award, the Harold W. McGraw, Jr. Prize in Education, and the IEEE James H. Mulligan, Jr. Education Medal, among others.
Dr. Elisenda Grigsby
Elisenda Grigsby received her PhD in mathematics from UC, Berkeley in 2006, joined the math department at Boston College in 2009, and was awarded the AWM-Birman Research Prize in Topology and Geometry and the Presidential Early Career Award for Scientists and Engineers (PECASE) in 2015 and 2016, respectively, for her contributions to knot theory and low-dimensional topology. Shortly thereafter, she pivoted to studying the mathematical foundations of machine learning algorithms, focusing on geometric aspects of deep learning theory. Grigsby now holds a joint appointment in the CS department at BC, and co-directs the BC Experimental Math & Machine Learning Lab.
Dr. Haggai Maron
Dr. Haggai Maron is an Assistant Professor in the Faculty of Electrical and Computer Engineering at the Technion – Israel Institute of Technology and a Senior Research Scientist at NVIDIA Research. He focuses on deep learning for structured data, particularly sets, graphs, point clouds, weight spaces, and other data with inherent symmetry structures. Dr. Maron's work combines theoretical analysis and design of deep learning architectures with practical applications to real-world problems. Notable achievements include receiving the Outstanding Paper Award at ICML 2020, two Best Paper Awards at NeurIPS and ICML workshops in 2024, and the Alon scholarship for the integration of outstanding faculty from the Israel Council for Higher Education in 2024. He holds a Ph.D. in Computer Science and Mathematics from the Weizmann Institute of Science.
Dr. Robin Walters
Robin Walters is an assistant professor in the Khoury College of Computer Sciences at Northeastern University, based in Boston.
Walters’ research focuses on the role of symmetry in deep learning. By exploring ways of building a problem’s symmetry into a deep learning model as hard mathematical constraints, Walters has discovered it’s possible to improve not just that model’s data efficiency, but its generalization and trustworthiness as well. Now, as director of the Geometric Learning Lab, Walters is pushing the limits of these methods, making use of approximate symmetry and exploring everything from the theory of underlying symmetry in neural network structure to the subject’s range of practical applications.
Walters also brings his background as a mathematician into the classroom, where he teaches computational theory. He enjoys watching his students develop the ability to think rigorously and communicate clearly about the complex topic, and he particularly enjoys mentoring graduate students. Walters is a visiting fellow at the Boston Dynamics AI Institute, where he develops equivariant neural networks for sample efficient robot perception and manipulation.
Schedule
8:30 AM - 9:00 AM
Check-in
9:00 AM - 9:15 AM
Opening Remarks
9:15 AM - 10:00 AM
Keynote: Dr. Haggai Maron
10:00 AM - 10:30 AM
Coffee Break/ Hanging Posters
10:30 AM - 11:30 AM
Spotlight Talks
Paper 6: Achieving Approximate Symmetry Is Exponentially Easier than Exact Symmetry
Paper 37: Investigating Zero-Shot Size Transfer of Graph Neural Differential Equations for Learning Graph Diffusion Dynamics
Paper 9: Which Way from B to A: The role of embedding geometry in image interpolation for Stable Diffusion
Paper 4: Topological Preservation in Temporal Link Prediction
11:30 AM - 12:30 PM
Math Beyond Academia Panel
Panelists: Dr. Katie Rainey (Naval Information Warfare Center Pacific), Dr. Cayley Rice (Leidos), Dr. Christian Shewmake (New Theory AI), and Dr. Haggai Maron (Technion and NVIDIA Research)
Moderator: Dr. Tegan Emerson
12:30 PM - 2:00 PM
Lunch + Networking
2:00 PM - 2:45 PM
Keynote: Dr. Elisenda Grigsby
2:45 PM - 3:20 PM
Flash Talks
Paper 35: A Graph Laplacian Eigenvector-based Pre-training Method for Graph Neural Networks
Paper 43: Dispersing Embeddings in Transformer Layers Improves Generalization of Language Models
Paper 23: Topological Signatures of ReLU Neural Network Activation Patterns
Paper 29: Robust Hyperspectral Anomaly Detection via Bootstrap Sampling-based Subspace Modeling in the Signed Cumulative Distribution Transform Domain
Paper 32: Precision Matrix based Feature Learning Mechanism for Subspace Clustering Task
Paper 34: Self-Organizing Maps for the Reconstruction of Images in Pixel Permuted Image Stacks
Paper 41: Interpreting deep neural networks trained on elementary p groups reveals algorithmic structure
3:20 PM - 3:30 PM
Day 1 Remarks
3:30 PM - 4:00 PM
Break
4:00 PM - 5:15 PM
Poster Session-- All Papers
5:15 PM - 5:30 PM
Transition to Hosted Social Hour Location on Campus
5:30 PM -7:00 PM
Hosted Social Hour
9:00 AM - 9:15 AM
Opening Remarks
9:15 AM - 10:00 AM
Keynote: Dr. Richard Baraniuk
10:00 AM - 10:15 AM
TAG-DS Challenge Intro and Results
10:15 AM - 10:45 AM
Coffee Break/ Transition to Parallel Tracks
10:45 AM - 11:30 AM
Topology Talks/Algebra Talks/Geometry Talks Across 3 Rooms
Topology Talks
Paper 11: Quasi Zigzag Persistence: A Topological Framework for Analyzing Time-Varying Data
Paper 14: HAGGLE: Get a better deal using a Hierarchical Autoencoder for Graph Generation and Latent-space Expressivity
Paper 20: DYMAG: Rethinking Message Passing Using Dynamical-systems-based Waveforms
Algebra Talks
Paper 16: Algebraically-Informed Deep Networks: A Deep Learning Approach to Represent Algebraic Structures
Paper 19: Symmetry-Aware Graph Metanetwork Autoencoders: Model Merging through Parameter Canonicalization
Paper 28: A Model of Flocking Using Sheaves
Geometry Talks
Paper 2: Peeling metric spaces of strict negative type
Paper 12: Scratching the Surface: Reflections of Training Data Properties in Early CNN Filters
Paper 22: LINSCAN - A Linearity Based Clustering Algorithm
11:30 AM - 12:30 PM
Topology/Algebra/Geometry Collaboration Sessions Across 3 Rooms
12:30 PM - 2:00 PM
Lunch + Networking
2:00 PM - 2:45 PM
Keynote: Dr. Robin Walters
2:45 PM - 3:45 PM
TAG-DS Panel
Panelists: Dr. Richard Baraniuk, Dr. Elisenda Grigsby, Dr. Javier Duarte, Dr. Dima Drusvyatskiy, Dr. Yusu Wang
Moderator: Dr. Henry Kvinge
3:45 PM - 4:00 PM
Closing Remarks
Accepted Work
Charles Kulick, Björn Birnir, Sui Tang
(Spotlight) A Model of Flocking Using Sheaves
Joseph Geisz
(Spotlight) LINSCAN - A Linearity Based Clustering Algorithm
Andrew Dennehy, Xiaoyu Zou, Shabnam J. Semnani, Yuri Fialko, Alex Cloninger
(Spotlight) DYMAG: Rethinking Message Passing Using Dynamical-systems-based Waveforms
Dhananjay Bhaskar, Xingzhi Sun, Yanlei Zhang, Charles Xu, Arman Afrasiyabi, Siddharth Viswanath, Oluwadamilola Fasina, Guy Wolf, Michael Perlmutter, Smita Krishnaswamy
(Spotlight) Symmetry-Aware Graph Metanetwork Autoencoders: Model Merging through Parameter Canonicalization
Odysseas Boufalis, Jorge Carrasco-Pollo, Joshua Rosenthal, Eduardo Terres-Caballero, Alejandro García-Castellanos
(Spotlight) Algebraically-Informed Deep Networks: A Deep Learning Approach to Represent Algebraic Structures
Mustafa Hajij, Ghada Zamzmi, Matthew Dawson, Greg Muller, Theodore Papamarkou
Tegan Emerson, Audun D Myers, Stephen J. Young
(Spotlight) Scratching the Surface: Reflections of Training Data Properties in Early CNN Filters
Grayson Jorgenson, Cassie Heine, Robin Cosbey, Abby Reynolds, Davis Brown, Henry Kvinge, Timothy Doster, Tegan Emerson
(Spotlight) Quasi Zigzag Persistence: A Topological Framework for Analyzing Time-Varying Data
Tamal K. Dey, Shreyas N. Samaga
(Spotlight) Which Way from B to A: The role of embedding geometry in image interpolation for Stable Diffusion
Tegan Emerson, Luke Durell, Javier E. Flores, Nicholas Karris
(Spotlight) Achieving Approximate Symmetry Is Exponentially Easier than Exact Symmetry
Behrooz Tahmasebi, Melanie Weber
(Spotlight) Topological Preservation in Temporal Link Prediction
Marco Campos, William Ott, Henry Adams, Sarah E. Simpson, Dan J. Krofcheck, Casey Doyle, Michael Xi
(Spotlight) Peeling metric spaces of strict negative type
Steve Huntsman
(Flash talk) Dispersing Embeddings in Transformer Layers Improves Generalization of Language Models
Chen Liu, Xingzhi Sun, Alexandre Van Tassel, Xi Xiao, Kristof Reimann, Danqi Liao, Ke Xu, Tianyang Wang, Xiao Wang, Smita Krishnaswamy
(Flash talk) Interpreting deep neural networks trained on elementary p groups reveals algorithmic structure
Gavin McCracken, Arthur Ayestas Hilgert, Sihui Wei, Gabriela Moisescu-Pareja, Zhaoyue Wang, Jonathan Love
(Flash talk) A Graph Laplacian Eigenvector-based Pre-training Method for Graph Neural Networks
Howard Dai, Nyambura Njenga, Hiren Madhu, Siddharth Viswanath, Ryan Pellico, Ian Adelstein, Smita Krishnaswamy
(Flash talk) Self-Organizing Maps for the Reconstruction of Images in Pixel Permuted Image Stacks
Connor Price, Michael Kirby, Christopher Scott Peterson, David Kott
(Flash talk) Precision Matrix based Feature Learning Mechanism for Subspace Clustering Task
Haohan Zou, Alex Cloninger
Abu Hasnat Mohammad Rubaiyat, Jordan Vincent, Colin Olson
(Flash talk) Topological Signatures of ReLU Neural Network Activation Patterns
Vicente Bosca, Tatum Rask, Sunia Tanweer, Andrew R. Tawfeek, Branden Stone
(Poster) Comparative Analysis in Pre‑image Algorithms of Kernel PCA
Canran Ji, Wojciech Czaja
(Poster) The Geometry and Topology of Modular Addition Representations
Gabriela Moisescu-Pareja, Gavin McCracken, Harley Wiltzer, Colin Daniels, Vincent Létourneau, Doina Precup, Jonathan Love
James Amarel, Nicolas Hengartner, Robyn Miller, Benjamin Migliori, Daniel Hope, Emily Casleton, Alexei Skurikhin, Earl Lawrence, Gerd J. Kunde
(Poster) Reeb Graphs and Towers: Multiscale Skeletons for Data
Andrew J Steindl, Dhananjay Bhaskar, Smita Krishnaswamy
Henry Kvinge, Andrew Aguilar, Nayda Farnsworth, Grace O’Brien, Sarah McGuire Scullen, Robert Jasper, Helen Jenne
(Poster) Using Local Complexity to Evaluate Out-of-Distribution Generalization
Grace O'Brien, Andrew Aguilar, Robert Jasper, Henry Kvinge, Sarah McGuire Scullen, Helen Jenne
(Poster) Governing Equation Discovery with Relaxed Symmetry Constraints
Andrew J Chen, Jianke Yang, Rose Yu
(Poster) Multi-View Graph Learning with Graph-Tuple
Shiyu Chen, Ningyuan Huang, Soledad Villar
(Poster) Looping back: Circular nodes revisited with novel applications in the radio frequency domain
Tegan Emerson, Tim Marrinan, Bill Kay, Rachel Wofford, Audun D Myers
Zhaiming Shen, Sung Ha Kang
(Poster) Kernel Mean Embeddings of [CLS] Tokens in ViTs
Mason D. Faldet
(Poster) Learning Polynomial Activation Functions for Deep Neural Networks
Linghao Zhang, Jiawang Nie, Tingting Tang
(Poster) Neural Local Wasserstein Regression
Inga Girshfeld, Xiaohui Chen
(Poster) Bilevel Optimization for Hyperparameter Learning in Supporting Vector Machines
Lei Huang, Jiawang Nie, Jiajia Wang, Suhan Zhong
(Poster) LR-RaNN: Lipschitz Regularized Randomized Neural Networks for System Identification
Chunyang Liao
TAG-DS: TAG... We're it! Senior Organizing Committee
Dr. Tegan Emerson
Pacific Northwest National Laboratory
University of Texas El Paso
Colorado State University
Dr. Alex Cloninger
University of California San Diego
Dr. Bastian Grossenbacher Rieck
University of Fribourg
Dr. Gal Mishne
University of California San Diego
Dr. Henry Kvinge
Pacific Northwest National Laboratory
University of Washington
Dr. Yusu Wang
University of California San Diego
Dr. Katie Rainey
Naval Information Warfare Center Pacific
Dr. Timothy Doster
Pacific Northwest National Laboratory
TAG-DS: TAG... We're it! Program Committee
Topology Area Chair
Mitchell Black
University of California San Diego
Algebra Area Chair
Henry Kvinge
Pacific Northwest National Laboratory
Geometry Area Chair
Qingsong Wang
University of California San Diego
DS Area Chair
Chester Holtz
University of California San Diego
Proceedings Chair
Alison Pouplin
Aalto University
Poster Chair
Eric Yeats
Pacific Northwest National Laboratory
Speaker & Panel Chair
Jianke Yang
University of California San Diego
Submission Chair
Ińes García-Rodondo
London School of Geometry and Number Theory
Challenge Co-Chair
Guillermo Bernardez Gil
University of California Santa Barbara
Challenge Co-Chair
Lev Telyatnikov
École Polytechnique Fédérale de Lausanne
Challenge Co-Chair
Mit Kotak
Massachusetts Institute of Technology
Challenge Co-Chair
Mathilde Papillon
University of California Santa Barbara
Open Review Chair
Jeremy Wayland
Technical University of Munich
Sponsors
Templates
Paper Template-- make sure to submit your camera-ready version with all author information and no checklist!
Archival Paper Copyright Form -- All archival papers require a signed copyright form to be included in the associated proceedings. Please upload this and the requested .bib file along with your camera-ready paper to OpenReview. If you have any issues, you can send to info@tagds.com. The signed form should be labeled as lastname25Permission.pdf where "lastname" is the surname of the first author in all lowercase.
Optional Poster Template -- if you elect to use a different template, please ensure that your poster dimensions are 36" wide by 24" tall.
Optional 5-minute Flash Talk Template -- You are welcome to use beamer or another template but the 5-minute talks must be only 4 slides: title with acknowledgements, problem statement/motivation, technical approach, and key findings.
Optional 15-minute Spotlight Talk Template -- You are welcome to use beamer or another template. The 15-minutes includes questions so please plan accordingly!