Hello! I’m a postdoc at Harvard University, hosted by Prof. Heng Yang. Previously, I had a blast doing my phd at Boston University, advised by Prof. Yannis Paschalidis and Prof. Ashok Cutkosky. Long ago I did my undergrad at Tsinghua University.
I’m broadly interested in sequential data science. How do we process information revealed on a data stream, and rigorously use that to support real-time decision making? For me, this is a fascinating field at the intersection of optimization, signal processing, statistics and game theory.
Specifically, my research centers around adaptive online learning. The goal is to design online decision making algorithms that Bayes-optimally exploit offline knowledge, such as domain structures, physical models and deep learning. I envision it as a bridge between offline methods and their robust online deployment against uncertainties.
Recently I’m also excited about bringing such algorithmic advances closer to the real world, particularly in the area of robotics and automation.
Email address: zhiyuz [at] seas (dot) harvard (dot) edu
CV Github Google Scholar Semantic Scholar
Publication
Five representative works marked with [*].
-
[*] The Benefit of Being Bayesian in Online Conformal Prediction
ZZ, Zhou Lu, Heng Yang.
Preprint. -
Adapting Conformal Prediction to Distribution Shifts Without Labels
Kevin Kasa, ZZ, Heng Yang, Graham Taylor.
Preprint. -
[*] Fast TRAC: A Parameter-Free Optimizer for Lifelong Reinforcement Learning
Aneesh Muppidi, ZZ, Heng Yang.
NeurIPS 2024. -
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. -
[*] 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. -
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