Research
Research
(α-β) alphabetical order; * joint first
Manuscripts
Optimal use of a black-box model in semiparametric estimation. [arxiv]
Yihong Gu
Under review
Unveiling the invariant factors across heterogeneous environments via ATLAS. [arxiv]
Yihong Gu, Kathrine Liao, Tianxi Cai
Under review
Optimally taming biases in black-box models for efficient semiparametric estimation. [arxiv]
Yihong Gu, Qishuo Yin, Tianxi Cai, Jianqing Fan
Major revision at Annals of Statistics
Neural Generative Distributional Regression. [arxiv]
Jinhang Chai, Jianqing Fan, Yihong Gu (α-β)
Under review
Near-Optimal Tensor PCA via Normalized Stochastic Gradient Ascent with Overparameterization. [arxiv]
Shihong Ding, Yihong Gu, Yuanshi Liu, Cong Fang
Under revision
Optimal estimation of a factorizable density using diffusion models with ReLU neural networks. [arxiv]
Jianqing Fan, Yihong Gu, Ximing Li (α-β)
Under revision
CINDES: Classification induced neural density estimator and simulator. [arxiv]
Dehao Dai, Jianqing Fan, Yihong Gu, Debarghya Mukherjee (α-β)
Major revision at JASA
Fundamental Computational Limits in Pursuing Invariant Causal Prediction and Invariance-Guided Regularization. [arxiv]
Yihong Gu, Cong Fang, Yang Xu, Zijian Guo, Jianqing Fan
Under revision
Journal Publications
Causality Pursuit from Heterogeneous Environments via Neural Adversarial Invariance Learning. [arxiv] [code]
Yihong Gu, Cong Fang, Peter Bühlmann, Jianqing Fan
Annals of Statistics, 53(5): 2230-2257, 2025
Jianqing Fan, Cong Fang, Yihong Gu, Tong Zhang (α-β)
Annals of Statistics, 52(5): 2268-2292, 2024.
ASA Best Student Paper Award at the Business and Economic Statistics Session, 2024
IMS Hannan Graduate Student Travel Award, 2024
How do noise tails impact on deep ReLU networks? [arxiv]
Jianqing Fan, Yihong Gu, Wen-Xin Zhou (α-β)
Annals of Statistics, 52 (4): 1845-1871, 2024.
Factor Augmented Sparse Throughput Deep ReLU Neural Networks for High Dimensional Regression. [arxiv] [code]
Jianqing Fan, Yihong Gu (α-β)
Journal of the American Statistical Association, 119(548), 2680–2694, 2024.
Convex Formulation of Overparameterized Deep Neural Networks.
Cong Fang, Yihong Gu, Weizhong Zhang, Tong Zhang
IEEE Transactions on Information Theory, 2022
Conference Publications
The Implicit Bias of Heterogeneity towards Invariance: A Study of Multi-Environment Matrix Sensing. [arxiv]
Yang Xu*, Yihong Gu*, Cong Fang
Annual Conference on Neural Information Processing System (NeurIPS), 2024
How to Characterize The Landscape of Overparameterized Convolutional Neural Networks.
Yihong Gu*, Weizhong Zhang*, Cong Fang, Jason D. Lee, Tong Zhang
Annual Conference on Neural Information Processing Systems (NeurIPS), 2020
Language modeling with sparse product of sememe experts. [arxiv]
Yihong Gu*, Jun Yan*, Hao Zhu*, Zhiyuan Liu, Ruobing Xie, Maosong Sun, Fen Lin, Leyu Lin
Empirical Methods in Natural Language Processing (EMNLP), 2018
Miscellaneous
Open problem: Structure-agnostic minimax risk for partial linear model.
Yihong Gu
Annual Conference on Learning Theory (COLT), 2025. [Open problem track].