37 citations · 88 across the 14 of their papers we have counts for
14 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 $π_…
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…
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…
Fundamental Computational Limits in Pursuing Invariant Causal Prediction and Invariance-Guided Regularization
Yihong Gu, Cong Fang, Yang Xu +2
Pursuing invariant prediction from heterogeneous environments opens the door to learning causality in a purely data-driven way and has several applications in causal discovery and…
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…
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…
Environment Invariant Linear Least Squares
Jianqing Fan, Cong Fang, Yihong Gu +1
This paper considers a multi-environment linear regression model in which data from multiple experimental settings are collected. The joint distribution of the response variable an…
Factor Augmented Sparse Throughput Deep ReLU Neural Networks for High Dimensional Regression
Jianqing Fan, Yihong Gu
This paper introduces a Factor Augmented Sparse Throughput (FAST) model that utilizes both latent factors and sparse idiosyncratic components for nonparametric regression. The FAST…
How do noise tails impact on deep ReLU networks?
Jianqing Fan, Yihong Gu, Wen-Xin Zhou
This paper investigates the stability of deep ReLU neural networks for nonparametric regression under the assumption that the noise has only a finite p-th moment. We unveil how the…
Convex Formulation of Overparameterized Deep Neural Networks
Cong Fang, Yihong Gu, Weizhong Zhang +1
Analysis of over-parameterized neural networks has drawn significant attention in recentyears. It was shown that such systems behave like convex systems under various restrictedset…
Domain Adaptive Imitation Learning
Kuno Kim, Yihong Gu, Jiaming Song +2
We study the question of how to imitate tasks across domains with discrepancies such as embodiment, viewpoint, and dynamics mismatch. Many prior works require paired, aligned demon…
Language Modeling with Sparse Product of Sememe Experts
Yihong Gu, Jun Yan, Hao Zhu +5
Most language modeling methods rely on large-scale data to statistically learn the sequential patterns of words. In this paper, we argue that words are atomic language units but no…
ZhuSuan: A Library for Bayesian Deep Learning
Jiaxin Shi, Jianfei Chen, Jun Zhu +4
In this paper we introduce ZhuSuan, a python probabilistic programming library for Bayesian deep learning, which conjoins the complimentary advantages of Bayesian methods and deep…