Data Science Seminars

The IMA Data Science Seminar hosts research talks that are broadly related to the areas of data science and machine learning, which may include theoretical work on mathematical foundations of data science, interactions between data science and other domains, as well as applications of data science in science and engineering. The goal of the seminar is to bring together faculty, postdocs, students, and industrial partners who are interested in data science and broadly related fields to exchange ideas and foster collaborations.

The seminars are organized by Jeff Calder, Jasmine Foo, Will Leeb, Gilad Lerman, Yulong Lu, and Li Wang  of the School of Mathematics at the University of Minnesota, and will generally take place Tuesdays from 1:25-2:25 p.m. in Lind Hall 325 or via Zoom. Please check the individual seminar page for details.

Past seminars

Expand all



September 12, 2023

Large data limit of the MBO scheme for data clustering 
Jona Lelmi (University of California, Los Angeles)

September 26, 2023

Information Gamma calculus: Convexity analysis for stochastic differential equations 
Wuchen Li (University of South Carolina)

October 3, 2023

Exploiting geometric structure in matrix-valued optimization 
Melanie Weber (Harvard University)

October 10, 2023

How much can one learn a PDE from its solution?
Yimin Zhong (Auburn University)

October 17, 2023

Computational mean-field games: from conventional methods to deep generative models
Jiajia Yu (Duke University)

October 24, 2023

Trading off accuracy for reduced computation in scientific computing 
Alex Gittens (Rensselaer Polytechnic Institute)

October 31, 2023

Data Driven Modeling of Unknown Systems with Deep Neural Networks
Dongbin Xiu (The Ohio State University)

November 14, 2023

Normalization effects and mean field theory for deep neural networks
Konstantinos Spiliopoulos (Boston University)

November 21, 2023

Transferability of Graph Neural Networks using Graphon and Sampling Theories
Martina Neuman (University of Vienna)

November 28, 2023

The Kagome lattice as a mechanism-based mechanical metamaterial
Xuenan Li (Columbia University)

December 5, 2023

Learning in the presence of low-dimensional structure: a spiked random matrix perspective
Denny Wu (New York University)

January 30, 2024

Optimal Transport Maps for Conditional Simulation 
Bamdad Hosseini (University of Washington)

February 13, 2024

Generalization theory for diffusion models
Frank Cole (University of Minnesota)

February 20, 2024

The effect of Leaky ReLUs on the training and generalization of overparameterized networks 
Yinglong Guo (University of Minnesota)

February 27, 2024

Improved Convergence Rates of Anderson Acceleration for a Large Class of Fixed-Point Iterations
Casey Garner (University of Minnesota)

March 12, 2024

Random High-Dimensional Binary Vectors, Kernel Methods, and Hyperdimensional Computing
Nicholas Marshall (Oregon State University)

March 19, 2024

Fourier representations for fast Gaussian process regression
Philip Greengard (Columbia University)

March 26, 2024

On small and large scales in training physics-informed neural networks for partial differential equations
Zhongqiang Zhang (Worcester Polytechnic Institute)

April 2, 2024

Advancing Machine-Learned Interatomic Potentials: Enhancing Accuracy and Robustness in Materials Science Applications
Yangshuai Wang (University of British Columbia)

April 9, 2024

Spatial Stochastic modeling for population dynamic
Wai-Tong (Louis) Fan (Indiana University)

April 16, 2024

Are the measurement data enough: an instability study for an inverse problem for the stationary radiative transport near the diffusion limit
Hongkai Zhao (Duke University)

April 23, 2024

Numerical Methods of Neural Network Discretization for Solving Nonlinear Differential Equations
Wenrui Hao (The Pennsylvania State University)

April 26, 2024

Local geometry determines global landscape in low-rank factorization for synchronization
Shuyang Ling (New York University)

April 30, 2024

Generative Machine Learning Models for Uncertainty Quantification
Guannan Zhang (Oak Ridge National Laboratory (ORNL))



May 2, 2023

ScreeNOT: Optimal Singular Value Thresholding and Principal Component Selection in Correlated Noise 
Elad Romanov (Stanford University)

April 11, 2023

Learning in Stochastic Games 
Muhammed Omer Sayin (Bilkent University)

April 4, 2023

Continuous-time probabilistic generative models for dynamic networks
Kevin Xu (Case Western Reserve University)

March 28, 2023

Viewing graph solvability and its relevance in 3D Computer Vision
Federica Arrigoni (Politecnico di Milano)

March 21, 2023

Adversarial training and the generalized Wasserstein barycenter problem
Matt Jacobs (Purdue University)

March 16, 2023

Overparametrization in machine learning: insights from linear models
Andrea Montanari (Stanford University)

February 21, 2023

Taming Nonconvexity in Tensor Completion: Fast Convergence and Uncertainty Quantification
Lecture: Yuxin Chen (University of Pennsylvania)

February 14, 2023

The Geometry of Molecular Conformations in Cryo-EM
Lecture: Roy Lederman (Yale University)

February 7, 2023

Multi-reference alignment: Representation theory perspective, sparsity, and projection-based algorithm
Lecture: Tamir Bendory (Tel Aviv University)

January 31, 2023

Efficient Invariant Embeddings for Universal Equivariant Learning
Lecture: Nadav Dym (Technion-Israel Institute of Technology)

January 24, 2023

Spectral norm of random matrices
Lecture: March Boedihardjo (ETH Zürich)

January 17, 2023

Two estimation problems for dynamical systems: linear systems on graphs, and interacting particle systems
Lecture: Mauro Maggioni (Johns Hopkins University)

December 13, 2022

Optimal shrinkage of singular values under noise with separable covariance & its application to fetal ECG analysis
Lecture: Pei-Chun Su (Duke University)

December 6, 2022

Equivariant machine learning
Soledad Villar (John Hopkins University)

November 29, 2022

Benefits of Weighted Training in Machine Learning and PDE-based Inverse Problems
Lecture: Yunan Yang (ETH Zürich)

November 22, 2022

Probabilistic Inference on Manifolds and Its Applications in 3D Vision 
Tolga Birdal (Imperial College London)

November 15, 2022

A PDE-Based Analysis of the Symmetric Two-Armed Bernoulli Bandit
Vladimir Kobzar (Columbia University)

November 8, 2022

Three Uses of Semidefinite Programming in Approximation Theory
Simon Foucart (Texas A & M University)

October 18, 2022

3-D reconstruction in macro- and micro-worlds: Challenges and Solutions 
Yunpeng Shi (Princeton University)

October 11, 2022

Does the Data Induce Capacity Control in Deep Learning? 
Pratik Chaudhari (University of Pennsylvania)

October 4, 2022

Cubic-Regularized Newton for Spectral Constrained Matrix Optimization and its Application to Fairness
Casey Garner (University of Minnesota, Twin Cities)

September 21, 2022

Multiscale analysis of manifold-valued curves 
Nir Sharon (Tel Aviv University)

September 20, 2022

Flexible multi-output multifidelity uncertainty quantification via MLBLUE 
Matteo Croci (The University of Texas at Austin)

September 13, 2022

The Back-And-Forth Method For Wasserstein Gradient Flows
Wonjun Lee (University of Minnesota, Twin Cities)



May 3, 2022 

Free Boundary Problems on Lattices
Charles Smart (Yale University)

April 26, 2022

A Distributed Linear Solver via the Kaczmarz Algorithm
Eric Weber (Iowa State University)

April 19, 2022

A Characteristics-based Approach to Computing Tukey Depths
Martin Molina-Fructuoso (North Carolina State University)

April 12, 2022

How Well Can We Generalize Nonlinear Learning Models in High Dimensions??
Inbar Seroussi (Weizmann Institute of Science)

April 5, 2022

Method of Moments: From Sample Complexity to Efficient Implicit Computations
Joao Pereira (The University of Texas at Austin)

March 29, 2022

Relaxing Gaussian Assumptions in High Dimensional Statistical Procedures
Larry Goldstein (University of Southern California)

March 22, 2022

Using Artificial Intelligence to Model and Support the Management of Multimorbid Patients
Martin Michalowski (University of Minnesota, Twin Cities)

March 15, 2022

Auto-differentiable Ensemble Kalman Filters
Daniel Sanz-Alonso (University of Chicago)

March 1, 2022

On Multiclass Adversarial Training, Perimeter Minimization, and Multimarginal Optimal Transport Problems
Nicolas Garcia Trillos (University of Wisconsin, Madison)

February 22, 2022

Integrative Discriminant Analysis Methods for Multi-view Data
Sandra Safo (University of Minnesota, Twin Cities)

February 15, 2022

Graph Clustering Dynamics: From Spectral to Mean Shift
Katy Craig (University of California, Santa Barbara)

February 8, 2022

Decomposing Low-Rank Symmetric Tensors
Joe Kileel (The University of Texas at Austin)

February 1, 2022

Stability and Generalization in Graph Convolutional Neural Networks
Ron Levie (Ludwig-Maximilians-Universität München)

January 25, 2022

Intelligent Randomized Algorithms for the Low CP-Rank Tensor Approximation Problem
Alex Gittens (Rensselaer Polytechnic Institute)

December 14, 2021

New Methods for Disease Prediction using Imaging and Genomics
Eran Halperin (UnitedHealth Group)

November 23, 2021

The Scattering Transform for Texture Synthesis and Molecular Generation
Michael Perlmutter (University of California, Los Angeles)

November 9, 2021

Non-Parametric Estimation of Manifolds from Noisy Data
Yariv Aizenbud (Yale University)

October 19, 2021

Data depths meet Hamilton-Jacobi equations
Ryan Murray (North Carolina State University)

October 12, 2021

Organizational Collaboration with Assisted Learning
Jie Ding (University of Minnesota, Twin Cities)

October 5, 2021

Scalable and Sample-Efficient Active Learning for Graph-Based Classification
Kevin Miller (University of California, Los Angeles)

September 28, 2021

Standardizing the Spectra of Count Data Matrices by Diagonal Scaling
Boris Landa (Yale University)

September 21, 2021

Handling model uncertainties via informative Goodness-of-Fit 
Sara Algeri (University of Minnesota, Twin Cities)

September 14, 2021

PDE-inspired Methods for Graph-based Semi-supervised Learning
Jeff Calder (University of Minnesota, Twin Cities)a, Twin Cities)