8 papers
Optimal use of a black-box learner in semiparametric estimation
Yihong Gu
Consider the partial linear model and in the structure-agnostic setting, where we are blind to the structure and…
Unveiling Invariant and Transferable Latent Factors Across Heterogeneous Environments via ATLAS
Yihong Gu, Katherine Liao, Tianxi Cai
This paper considers a multi-environment factor model in which high-dimensional covariates are collected from heterogeneous environments, with auxiliary labels available in a subse…
Optimally taming biases in black-box models for efficient semiparametric estimation
Yihong Gu, Qishuo Yin, Tianxi Cai +1
Modern semiparametric estimation often relies on flexible black-box machine learning methods to estimate nuisance functions, raising a fundamental question: how do nuisance estimat…
Causality Pursuit from Heterogeneous Environments via Neural Adversarial Invariance Learning
Yihong Gu, Cong Fang, Peter Bühlmann +1
Pursuing causality from data is a fundamental problem in scientific discovery, treatment intervention, and transfer learning. This paper introduces a novel algorithmic method for a…
Near-Optimal Tensor PCA via Normalized Stochastic Gradient Ascent with Overparameterization
Shihong Ding, Yihong Gu, Yuanshi Liu +1
We study the Order- () spiked tensor model for the tensor principal component analysis (PCA) problem: given i.i.d. observations of a -th order tensor generated…
The Implicit Bias of Heterogeneity towards Invariance: A Study of Multi-Environment Matrix Sensing
Yang Xu, Yihong Gu, Cong Fang
Models are expected to engage in invariance learning, which involves distinguishing the core relations that remain consistent across varying environments to ensure the predictions…