Haodong Liang — accepted AI-conference papers

2026

Differentially Private Two-Stage Gradient Descent for Instrumental Variable Regression

Haodong Liang, Yanhao Jin, Krishna Balasubramanian, Lifeng Lai

ICLR 2026poster

We study instrumental variable regression (IVaR) under differential privacy constraints. Classical IVaR methods (like two-stage least squares regression) rely on solving moment equations that directly use sensitive covariates and instruments, creating significant risks of privacy leakage and posing…

Cited by 0 Source ↗Scholar ↗

2025

Transformers Handle Endogeneity in In-Context Linear Regression

Haodong Liang, Krishna Balasubramanian, Lifeng Lai

ICLR 2025poster

We explore the capability of transformers to address endogeneity in in-context linear regression. Our main finding is that transformers inherently possess a mechanism to handle endogeneity effectively using instrumental variables (IV). First, we demonstrate that the transformer architecture can emul…

Cited by 2 Source ↗PDF ↗Scholar ↗