332 citations · 962 across the 43 of their papers we have counts for
44 papers
Experimental Design When N Equals One
Wenxuan Guo, Tengyuan Liang
N-of-1 trials, or time-series experiments, are widely used in clinical research and online platforms. Yet the theoretically optimal design for estimating many treatment effects rem…
A Markov Chain Approach to Preference Alignment
Takuya Koriyama, Tengyuan Liang
We propose Markov Chain from Human Feedback (MCHF), an elementary approach for aligning generative models from pairwise human preferences. Unlike Reinforcement Learning from Human…
Nonparametric Point Identification of Treatment Effect Distributions via Rank Stickiness
Tengyuan Liang
Treatment effect distributions are not identified without restrictions on the joint distribution of potential outcomes. Existing approaches either impose rank preservation -- a str…
Distributional Shrinkage II: Higher-Order Scores Encode Brenier Map
Tengyuan Liang
Consider the additive Gaussian model , where is an unknown signal, is independent of , and is known. Let denote the law of .…
Distributional Shrinkage I: Universal Denoiser Beyond Tweedie's Formula
Tengyuan Liang
We study the problem of denoising when only the noise level is known, not the noise distribution. Independent noise corrupts a signal , yielding the observation …
No-Regret Generative Modeling via Parabolic Monge-Ampère PDE
Nabarun Deb, Tengyuan Liang
We introduce a novel generative modeling framework based on a discretized parabolic Monge-Ampère PDE, which emerges as a continuous limit of the Sinkhorn algorithm commonly used in…
Gaussianized Design Optimization for Covariate Balance in Randomized Experiments
Wenxuan Guo, Tengyuan Liang, Panos Toulis
Achieving covariate balance in randomized experiments enhances the precision of treatment effect estimation. However, existing methods often require heuristic adjustments based on…
Temporal Wasserstein Imputation: A Versatile Method for Time Series Imputation
Shuo-Chieh Huang, Tengyuan Liang, Ruey S. Tsay
Missing data can significantly hamper standard time series analysis, yet they occur frequently in applications. In this paper, we introduce temporal Wasserstein imputation, a novel…
Denoising Diffusions with Optimal Transport: Localization, Curvature, and Multi-Scale Complexity
Tengyuan Liang, Kulunu Dharmakeerthi, Takuya Koriyama
Adding noise is easy; what about denoising? Diffusion is easy; what about reverting a diffusion? Diffusion-based generative models aim to denoise a Langevin diffusion chain, moving…
A Convexified Matching Approach to Imputation and Individualized Inference
YoonHaeng Hur, Tengyuan Liang
We introduce a new convexified matching method for missing value imputation and individualized inference inspired by computational optimal transport. Our method integrates favorabl…
Learning When the Concept Shifts: Confounding, Invariance, and Dimension Reduction
Kulunu Dharmakeerthi, YoonHaeng Hur, Tengyuan Liang
Practitioners often face the challenge of deploying prediction models in new environments with shifted distributions of covariates and responses. With observational data, such shif…
Randomization Inference When N Equals One
Tengyuan Liang, Benjamin Recht
N-of-1 experiments, where a unit serves as its own control and treatment in different time windows, have been used in certain medical contexts for decades. However, due to effects…
Detecting Weak Distribution Shifts via Displacement Interpolation
YoonHaeng Hur, Tengyuan Liang
Detecting weak, systematic distribution shifts and quantitatively modeling individual, heterogeneous responses to policies or incentives have found increasing empirical application…
Blessings and Curses of Covariate Shifts: Adversarial Learning Dynamics, Directional Convergence, and Equilibria
Tengyuan Liang
Covariate distribution shifts and adversarial perturbations present robustness challenges to the conventional statistical learning framework: mild shifts in the test covariate dist…
High-dimensional Asymptotics of Langevin Dynamics in Spiked Matrix Models
Tengyuan Liang, Subhabrata Sen, Pragya Sur
We study Langevin dynamics for recovering the planted signal in the spiked matrix model. We provide a "path-wise" characterization of the overlap between the output of the Langevin…
Online Learning to Transport via the Minimal Selection Principle
Wenxuan Guo, YoonHaeng Hur, Tengyuan Liang +1
Motivated by robust dynamic resource allocation in operations research, we study the \textit{Online Learning to Transport} (OLT) problem where the decision variable is a probabilit…
Reversible Gromov-Monge Sampler for Simulation-Based Inference
YoonHaeng Hur, Wenxuan Guo, Tengyuan Liang
This paper introduces a new simulation-based inference procedure to model and sample from multi-dimensional probability distributions given access to i.i.d.\ samples, circumventing…
Universal Prediction Band via Semi-Definite Programming
Tengyuan Liang
We propose a computationally efficient method to construct nonparametric, heteroscedastic prediction bands for uncertainty quantification, with or without any user-specified predic…
Interpolating Classifiers Make Few Mistakes
Tengyuan Liang, Benjamin Recht
This paper provides elementary analyses of the regret and generalization of minimum-norm interpolating classifiers (MNIC). The MNIC is the function of smallest Reproducing Kernel H…
Deep Learning for Individual Heterogeneity
Max H. Farrell, Tengyuan Liang, Sanjog Misra
This paper integrates deep neural networks (DNNs) into structural models to increase flexibility and capture rich heterogeneity while preserving interpretability. Economic (or scie…
Mehler's Formula, Branching Process, and Compositional Kernels of Deep Neural Networks
Tengyuan Liang, Hai Tran-Bach
We utilize a connection between compositional kernels and branching processes via Mehler's formula to study deep neural networks. This new probabilistic insight provides us a novel…
A Precise High-Dimensional Asymptotic Theory for Boosting and Minimum--Norm Interpolated Classifiers
Tengyuan Liang, Pragya Sur
This paper establishes a precise high-dimensional asymptotic theory for boosting on separable data, taking statistical and computational perspectives. We consider a high-dimensiona…
Estimating Certain Integral Probability Metric (IPM) is as Hard as Estimating under the IPM
Tengyuan Liang
We study the minimax optimal rates for estimating a range of Integral Probability Metrics (IPMs) between two unknown probability measures, based on independent samples from the…
On the Minimax Optimality of Estimating the Wasserstein Metric
Tengyuan Liang
We study the minimax optimal rate for estimating the Wasserstein- metric between two unknown probability measures based on i.i.d. empirical samples from them. We show that e…