Manuscripts

• Causality Pursuit from Heterogeneous Environments via Neural Adversarial Invariance Learning. [arxiv]

Yihong Gu, Cong Fang, Peter Bühlmann, Jianqing Fan

In submission

• The Implicit Bias of Heterogeneity towards Invariance and Causality. [arxiv]

Yang Xu*, Yihong Gu*, Cong Fang, (joint first author)

In submission

• Environment Invariant Linear Least Squares. [arxiv]

Jianqing Fan, Cong Fang, Yihong Gu, Tong Zhang (alphabetical order)

Under minor revision at Annals of Statistics

Publications

• How do noise tails impact on deep ReLU networks? [arxiv]

Jianqing Fan, Yihong Gu, Wen-Xin Zhou (alphabetical order)

Annals of Statistics, to appear

• Factor Augmented Sparse Throughput Deep ReLU Neural Networks for High Dimensional Regression. [arxiv] [journal] [code]

Jianqing Fan, Yihong Gu (alphabetical order)

Journal of the American Statistical Association, to appear

• Convex Formulation of Overparameterized Deep Neural Networks. [paper]

Cong Fang, Yihong Gu, Weizhong Zhang, Tong Zhang

IEEE Transactions on Information Theory, 2022

• How to Characterize The Landscape of Overparameterized Convolutional Neural Networks. [paper]

Yihong Gu*, Weizhong Zhang*, Cong Fang, Jason D. Lee, Tong Zhang (joint first author)

NeurIPS 2020

• Language modeling with sparse product of sememe experts. [paper] [arxiv]

Yihong Gu*, Jun Yan*, Hao Zhu*, Zhiyuan Liu, Ruobing Xie, Maosong Sun, Fen Lin, Leyu Lin (joint first author)

EMNLP 2018