Publications Google Scholar

Please see my latest updates at ☝️

Publications and Preprints (By Year)

2025

• C. Cheng, J. Duchi. “Some Robustness Properties of Label Cleaning”, 2025.
  arXiv

• M. Celentano, C. Cheng, A. Pananjady, K.A. Verchand. “State evolution beyond first-order methods I: Rigorous predictions and finite-sample guarantees”, 2025.
  arXiv

2024

• C. Cheng, J. Duchi, D. Levy. “Geometry, Computation, and Optimality in Stochastic Optimization”, 2024.
  arXiv

• F. Areces, C. Cheng, J. Duchi, R. Kuditipudi. “Two Fundamental Limits for Uncertainty Quantification in Predictive Inference”, 2024. Proceedings of the Thirty-Seventh Conference on Learning Theory (COLT 2025).
  conference

2023

• C. Cheng, G. Cheng, J. Duchi. “Collaboratively Learning Linear Models with Structured Missing Data”, 2023. Advances in Neural Information Processing Systems (NeurIPS 2023).
  arXiv conference

• C. Cheng, A. Montanari. “Dimension Free Ridge Regression”, 2023. The Annals of Statistics, Vol. 52, No. 6, pp. 2879–2912, 2024.
  arXiv journal

2022

• C. Cheng, H. Asi, J. Duchi. “How Many Labelers Do You Have? A Closer Look at Gold-Standard Labels”, 2022.
  arXiv

• C. Cheng, J. Duchi, R. Kuditipudi. “Memorize to Generalize: on the Necessity of Interpolation in High Dimensional Linear Regression”, 2022. Proceedings of the Thirty-Fifth Conference on Learning Theory (COLT 2022).
  arXiv conference

2021

• M. Celentano, C. Cheng, A. Montanari. “The High-dimensional Asymptotics of First Order Methods with Random Data”, 2021.
  arXiv

2020

• S. Cen, C. Cheng, Y. Chen, Y. Wei, Y. Chi. “Fast Global Convergence of Natural Policy Gradient Methods with Entropy Regularization”, 2020. Operations Research, Vol. 69, No. 6, pp. 1716–1731, 2021.
  arXiv journal

• C. Cheng, Y. Wei, Y. Chen. “Tackling Small Eigen-gaps: Fine-Grained Eigenvector Estimation and Inference under Heteroscedastic Noise”, 2020. IEEE Transactions on Information Theory, Vol. 67, No. 12, pp. 8152–8194, 2021.
  arXiv journal

2019

• Y. Chen, C. Cheng, J. Fan. “Asymmetry Helps: Eigenvalue and Eigenvector Analyses of Asymmetrically Perturbed Low-Rank Matrices”, 2019. The Annals of Statistics, Vol. 49, No. 1, pp. 435–458, 2021.
  arXiv journal

Thesis

“High dimensionality in modern machine learning: a random matrix theory perspective”.
Stanford University ProQuest Dissertations & Theses. 2025.