2 citations · 6 across the 16 of their papers we have counts for
17 papers
CyclOT: Learning Quadratic Optimal Transport Maps via Synchronized Forward-Backward Interpolants
Shizhou Xu, Jiachen Liu, Shih-Hsin Wang +4
We study the recovery of forward and reverse quadratic optimal-transport maps from unpaired samples in high dimensions. We introduce a bidirectional neural framework in which the l…
Observation geometry for uncertainty-aware Hamiltonian inference and experimental design in quantum magnets
Roy Liu, Venugopal Ranganathan, David Dahlbom +12
Determining microscopic interactions from spectroscopic and scattering measurements is central to understanding quantum materials, yet it often remains unclear which interactions c…
Mathematics of Data Science
Afonso S. Bandeira, Amit Singer, Thomas Strohmer
This book is about the mathematical foundations of data science. 1. Introduction 2. Curses, Blessings, and Surprises in High Dimensions 3. Singular Value Decomposition and Principa…
The "I Don't Know" Filter: Enhancing Agentic Reliability in Function Calling
Stefan Broecker, Mason del Rosario, Boris Selitser +1
The language models that underpin agents have seen a rapid rise in performance on function calling benchmarks. However, the metrics used in the training and evaluation of these mod…
Towards Multiscale Graph-based Protein Learning with Geometric Secondary Structural Motifs
Shih-Hsin Wang, Yuhao Huang, Taos Transue +4
Graph neural networks (GNNs) have emerged as powerful tools for learning protein structures by capturing spatial relationships at the residue level. However, existing GNN-based met…
Forgetting-MarI: LLM Unlearning via Marginal Information Regularization
Shizhou Xu, Yuan Ni, Stefan Broecker +1
As AI models are trained on ever-expanding datasets, the ability to remove the influence of specific data from trained models has become essential for privacy protection and regula…
The Future of Artificial Intelligence and the Mathematical and Physical Sciences (AI+MPS)
Andrew Ferguson, Marisa LaFleur, Lars Ruthotto +97
This community paper developed out of the NSF Workshop on the Future of Artificial Intelligence (AI) and the Mathematical and Physics Sciences (MPS), which was held in March 2025 w…
FedOSAA: Improving Federated Learning with One-Step Anderson Acceleration
Xue Feng, M. Paul Laiu, Thomas Strohmer
Federated learning (FL) is a distributed machine learning approach that enables multiple local clients and a central server to collaboratively train a model while keeping the data…
Machine Unlearning via Information Theoretic Regularization
Shizhou Xu, Thomas Strohmer
How can we effectively remove or ``unlearn'' undesirable information, such as specific features or the influence of individual data points, from a learning outcome while minimizing…
WHOMP: Optimizing Randomized Controlled Trials via Wasserstein Homogeneity
Shizhou Xu, Thomas Strohmer
We investigate methods for partitioning datasets into subgroups that maximize diversity within each subgroup while minimizing dissimilarity across subgroups. We introduce a novel p…
Differentially Private Synthetic High-dimensional Tabular Stream
Girish Kumar, Thomas Strohmer, Roman Vershynin
While differentially private synthetic data generation has been explored extensively in the literature, how to update this data in the future if the underlying private data changes…
Quantum paving: When sphere packings meet Gabor frames
Markus Faulhuber, Thomas Strohmer
We introduce the new problems of quantum packing, quantum covering, and quantum paving. These problems arise naturally when considering an algebra of non-commutative operators that…
Convergence Analysis of the Alternating Anderson-Picard Method for Nonlinear Fixed-point Problems
Xue Feng, M. Paul Laiu, Thomas Strohmer
Anderson Acceleration (AA) has been widely used to solve nonlinear fixed-point problems due to its rapid convergence. This work focuses on a variant of AA in which multiple Picard…
Improving Autoencoder Image Interpolation via Dynamic Optimal Transport
Xue Feng, Thomas Strohmer
Autoencoders are important generative models that, among others, have the ability to interpolate image sequences. However, interpolated images are usually not semantically meaningf…
On the (In)Compatibility between Group Fairness and Individual Fairness
Shizhou Xu, Thomas Strohmer
We study the compatibility between the optimal statistical parity solutions and individual fairness. While individual fairness seeks to treat similar individuals similarly, optimal…
Auto-Calibration and Biconvex Compressive Sensing with Applications to Parallel MRI
Yuan Ni, Thomas Strohmer
We study an auto-calibration problem in which a transform-sparse signal is acquired via compressive sensing by multiple sensors in parallel, but with unknown calibration parameters…
Private measures, random walks, and synthetic data
March Boedihardjo, Thomas Strohmer, Roman Vershynin
Differential privacy is a mathematical concept that provides an information-theoretic security guarantee. While differential privacy has emerged as a de facto standard for guarante…