Chi Jin - Statistical Learning

Statistical Learning

(α-β order) denotes alphabetical ordering, * denotes equal contribution.

Benign Overfitting in Out-of-Distribution Generalization of Linear Models [arXiv]

Maximum Likelihood Estimation is All You Need for Well-Specified Covariate Shift [arXiv]

On the Provable Advantage of Unsupervised Pretraining [arXiv]

A Local Convergence Theory for Mildly Over-Parameterized Two-Layer Neural Network [arXiv]

Provable Meta-Learning of Linear Representations [arXiv]

On the Theory of Transfer Learning: The Importance of Task Diversity [arXiv]

On the Local Minima of the Empirical Risk [arXiv]

Differentially Private Data Releasing for Smooth Queries [paper]

Ziteng Wang, Chi Jin, Kai Fan, Jiaqi Zhang, Junliang Huang, Yiqiao Zhong, Liwei Wang
Journal of Machine Learning (JMLR) 2015.

Dimensionality Dependent PAC-Bayes Margin Bound [paper]

Google Sites

Report abuse