Denoising Diffusions with Optimal Transport: Localization, Curvature, and Multi-Scale Complexity
Randomization Inference When N Equals One
A Convexified Matching Approach to Imputation and Individualized Inference
BUSN 41918 (PhD): Data, Learning, and Algorithms
Learning When the Concept Shifts: Confounding, Invariance, and Dimension Reduction
Detecting Weak Distribution Shifts via Displacement Interpolation
Blessings and Curses of Covariate Shifts: Adversarial Learning Dynamics, Directional Convergence, and Equilibria
High-dimensional Asymptotics of Langevin Dynamics in Spiked Matrix Models
Online Learning to Transport via the Minimal Selection Principle
Reversible Gromov-Monge Sampler for Simulation-Based Inference
Universal Prediction Band via Semi-Definite Programming
Interpolating Classifiers Make Few Mistakes
Mehler’s Formula, Branching Process, and Compositional Kernels of Deep Neural Networks
A Precise High-Dimensional Asymptotic Theory for Boosting and Minimum-L1-Norm Interpolated Classifiers
On the Multiple Descent of Minimum-Norm Interpolants and Restricted Lower Isometry of Kernels
Training Neural Networks as Learning Data-adaptive Kernels: Provable Representation and Approximation Benefits
Deep Neural Networks for Estimation and Inference
Just Interpolate: Kernel Ridgeless Regression Can Generalize
BUSN 41000 (MBA): Business Statistics
Local Optimality and Generalization Guarantees for the Langevin Algorithm via Empirical Metastability
How Well Generative Adversarial Networks Learn Distributions
Statistical Inference for the Population Landscape via Moment Adjusted Stochastic Gradients