Yiqiao Zhong

Publications

• Haolin Yang, Hakaze Cho, Yiqiao Zhong, Naoya Inoue (2025)
  Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning.
  Preprint [ArXiv version]

• Jingyang Lyu, Kangjie Zhou, and Yiqiao Zhong (2025)
  A statistical theory of overfitting for imbalanced classification.
  Preprint [ArXiv version], My blog

• Zhexuan Liu, Rong Ma, and Yiqiao Zhong (2025)
  Assessing and improving reliability of neighbor embedding methods: a map-continuity perspective.
  Nature Communications (2025) 16:5037 [Journal version], [ArXiv version], My blog

• Jiajun Song, Zhuoyan Xu, and Yiqiao Zhong (2025)
  Out-of-distribution generalization via composition: a lens through induction heads in Transformers.
  Proceedings of the National Academy of Sciences (direct submission) 122 (6) [Journal version], [ArXiv version], My blog

• Rheeya Uppaal, Apratim Dey, Yiting He, Yiqiao Zhong, Junjie Hu (2024)
  Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity.
  ICLR 2025 [ArXiv version]

• Harmon Bhasin, Timothy Ossowski, Yiqiao Zhong, and Junjie Hu (2024)
  How does Multi-Task Training Affect Transformer In-Context Capabilities? Investigations with Function Classes.
  NAACL 2024 [Conference version]

• Jiajun Song and Yiqiao Zhong (2023)
  Uncovering hidden geometry in Transformers via disentangling position and context.
  Preprint [ArXiv version], My blog

• Yu Gui, Cong Ma, and Yiqiao Zhong (2023)
  Unraveling Projection Heads in Contrastive Learning: Insights from Expansion and Shrinkage.
  Preprint [ArXiv version]

• Andrea Montanari, Yiqiao Zhong, and Kangjie Zhou (2022+)
  Tractability from overparametrization: The example of the negative perceptron.
  Probability Theory and Related Fields, To appear [ArXiv version]

• Montanari, A and Zhong, Y. (2022)
  The Interpolation Phase Transition in Neural Networks: Memorization and Generalization under Lazy Training.
  Annals of Statistics, 2022 [ArXiv version]

• Fan, J. Cong, M. and Zhong, Y. (2021)
  A Selective Overview of Deep Learning.
  Statistical Science, 2021 [ArXiv version].

• Fan, J. Wang, K. Zhong, Y. Zhu, Z. (2021)
  Robust High Dimensional Factor Models with Applications to Statistical Machine Learning
  Statistical Science, 2021 [ArXiv version]

• Avery, J. J., Starck, J., Zhong, Y., Avery, J. D., & Cooper, J. (2019+)
  When your own team is against you: Implicit and explicit attitudes in criminal defense
  The Journal of Social Psychology, 2020

• Fan, J. Zhong, Y. (2019+)
  Optimal Subspace Estimation Using Overidentifying Vectors via Generalized Method of Moments
  Preprint [ArXiv version]

• Zhong, Y. (2019+)
  Eigenvector Under Random Perturbation: A Nonasymptotic Rayleigh-Schrödinger Theory
  Preprint [ArXiv version]

• Abbe, E. Fan, J. Wang, K. Zhong, Y. (2019)
  Entrywise Eigenvector Analysis of Random Matrices with Low Expected Rank
  the Annals of Statistics, 2020 [ArXiv version], [Slides]

• Fan, J. Wang, W. and Zhong, Y. (2019)
  Robust Covariance Estimation for Approximate Factor Models
  Journal of Econometrics 208.1 (2019): 5-22. [ArXiv version].

• Zhong, Y. and Boumal, N. (2018)
  Near-optimal Bounds For Phase Synchronization
  SIAM Journal on Optimization, 28.2: 989-1016, 2018 [ArXiv Version], [SIAM version], [Slides], [Poster]
  Paper received SIAM best student paper prize at 2018 SIAM annual meeting; see [News & Media]

• Fan, J. Wang, W. and Zhong, Y. (2018)
  An Eigenvector Perturbation Bound and Its Application to Robust Covariance Estimation
  Journal of Machine Learning Research; 18(207):1−42, 2018 [ArXiv version], [JMLR version], [Slides], [Poster]

• Wang, Ziteng et al. (2016)
  Differentially Private Data Releasing for Smooth Queries
  Journal of Machine Learning Research; 17(51):1−42, 2016 [JMLR version]