Hello! I’m a researcher interested in the foundations of data science and automation. I will join Zhejiang University as an assistant professor in Spring 2026.

Bio.   I’m spending this fall as a postdoc at Carnegie Mellon University, hosted by Aaditya Ramdas. Previously I did my phd at Boston University, advised by Yannis Paschalidis and Ashok Cutkosky, and then spent two years as a postdoc at Harvard University, hosted by Heng Yang. Long ago I did my undergrad at Tsinghua University.

Research.   My past research centers around adaptive online learning, which concerns the theory and practice of sequential decision making with initial guesses. Recently I’ve also been working on uncertainty quantification, especially the use of regularization to relax “hard assumptions” on the nature. I enjoy thinking about properly abstracted theoretical problems, designing (hopefully) creative solutions by bridging ideas from disparate fields, and finally applying those to grand challenges in GenAI and automation. Here is my research statement.

I’m building a warm, supportive and intellectually stimulating research group at Zhejiang University to work on some fun topics. Please reach out if you are interested, thank you!

Email address: zhiyuzresearch [at] gmail (dot) com

CV   Github   Google Scholar   Photo

Publication

Five representative works

• The Benefit of Being Bayesian in Online Conformal Prediction
  ZZ, Zhou Lu, Heng Yang.
  Preprint.

• Fast TRAC: A Parameter-Free Optimizer for Lifelong Reinforcement Learning
  Aneesh Muppidi, ZZ, Heng Yang.
  NeurIPS 2024.

• Improving Adaptive Online Learning Using Refined Discretization
  ZZ, Heng Yang, Ashok Cutkosky, Ioannis Paschalidis.
  ALT 2024.

• Unconstrained Dynamic Regret via Sparse Coding
  ZZ, Ashok Cutkosky, Ioannis Paschalidis.
  NeurIPS 2023.

• Optimal Comparator Adaptive Online Learning with Switching Cost
  ZZ, Ashok Cutkosky, Ioannis Paschalidis.
  NeurIPS 2022. Also presented at ICML 2022 workshop.

Other works

• Population Dynamics Control with Partial Observations
  Zhou Lu, Y. Jennifer Sun, ZZ. (alphabetical order)
  Preprint.

• Sparsity-Based Interpolation of External, Internal and Swap Regret
  Zhou Lu, Y. Jennifer Sun, ZZ. (alphabetical order)
  COLT 2025.

• Adapting Conformal Prediction to Distribution Shifts Without Labels
  Kevin Kasa, ZZ, Heng Yang, Graham Taylor.
  UAI 2025.

• Discounted Adaptive Online Learning: Towards Better Regularization
  ZZ, David Bombara, Heng Yang.
  ICML 2024.

• Understanding Adam Optimizer via Online Learning of Updates: Adam is FTRL in Disguise
  Kwangjun Ahn, ZZ, Yunbum Kook, Yan Dai.
  ICML 2024.

• PDE-Based Optimal Strategy for Unconstrained Online Learning
  ZZ, Ashok Cutkosky, Ioannis Paschalidis.
  ICML 2022.

• Adversarial Tracking Control via Strongly Adaptive Online Learning with Memory
  ZZ, Ashok Cutkosky, Ioannis Paschalidis.
  AISTATS 2022.

• Provable Hierarchical Imitation Learning via EM
  ZZ, Ioannis Paschalidis.
  AISTATS 2021. Also presented at ICML 2020 Workshop.

PhD Dissertation.  Temporal Aspects of Adaptive Online Learning: Continuity and Representation