Research
My research is focused on developing machine learning methods capable of handling diverse and heterogeneous data sources. In particular, I utilize and develop techniques in optimal transport, Bayesian nonparametric models, domain adaptation/generalization, and large model pretraining & fine-tuning. The ultimate goal of my work is to enable generalizable and reliable machine learning applications in critical sectors, such as healthcare and robotics.
A preliminary clustering analysis of my works:
|
Updates
- 2023/08: I will give a talk at the Healthy ML lab, led by Prof. Marzyeh Ghassemi at MIT CSAIL, Thanks for hosting!
- 2023/06: I attended the CHIL 2023 Doctoral Symposium in Cambridge, MA.
- 2023/05: I started my research intern at the Health AI group of Apple AI/ML, stay heathy!
- 2023/04: I gave a talk on generalizable ML for cardiovascular health, hosted by Prof. Fei Fang. Thanks for hosting!
- 2023/04: Our work about robust learning on Wasserstein geodesics is accepted at ICML 2023! See you in Hawaii!
- 2023/02: Our two works about OT and LLMs on ECG data are accepted at ICASSP 2023 and EACL 2023!
- 2023/02: Among one of the 10% top reviewers for AISTATS 2023!
- 2022/09: Our work, "Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation" is accepted by NeurIPS 2022! Thanks to all wonderful contributors!
- 2022/08: I'm selected to be a recipient of 2022 Qualcomm Innovation Fellowship!
- 2022/04: Our work, "GeoECG: Data Augmentation via Wasserstein Geodesic Perturbation for Robust Electrocardiogram Prediction" is accepted by MLHC 2022! Thanks to all the awesome contributors!
- 2022/03: Our recent work, "PhysioMTL: Personalizing Physiological Patterns using Optimal Transport Multi-Task Regression" collaborated with Apple AI/ML, is accepted by CHIL 2022! Thanks to all the awesome contributors!
- 2021/07: I gave a talk on Functional Optimal Transport at UIUC Secure Learning Lab, hosted by Prof. Bo Li.
|
Selected publications & preprints
|
|
Functional optimal transport: map estimation and domain adaptation for functional data
Jiacheng Zhu*,
Aritra Guha*,
Dat Do*,
Mengdi Xu,
XuanLong Nguyen,
Ding Zhao.
Submitted to JMLR
arXiv /
code /
project page
|
|
Interpolation for Robust Learning: Data Augmentation on Wasserstein Geodesics
Jiacheng Zhu,
Jielin Qiu,
Aritra Guha,
Zhuolin Yang,
XuanLong Nguyen,
Bo Li,
Ding Zhao.
International Conference on Machine Learning (ICML) 2023
paper /
arXiv
|
|
Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment
Jielin Qiu,
Jiacheng Zhu,
Mengdi Xu,
Frank Dernoncourt,
Trung Bui,
Zhaowen Wang,
Bo Li,
Ding Zhao,
Hailin Jin.
Annual Meeting of the Association for Computational Linguistics (ACL)2023
paper /
arXiv /
Adobe Research
|
|
Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation
Peide Huang,
Mengdi Xu,
Jiacheng Zhu,
Laixi Shi,
Fei Fang,
Ding Zhao.
Conference on Neural Information Processing Systems (NeurIPS) 2022
paper /
arXiv
|
|
GeoECG: Data Augmentation via Wasserstein Geodesic Perturbation for Robust Cardiovascular Prediction
Jiacheng Zhu*,
Jielin Qiu*,
Zhuolin Yang,
Douglas Weber,
Michael Rosenberg,
Emerson Liu,
Bo Li,
Ding Zhao.
PMLR Machine Learning for Healthcare (MLHC) 2022, shorter version on ICLR 2022 SRML workshop
arXiv /
spotlight talk /
ICLR 2022 SRML Workshop
|
|
PhysioMTL: Personalizing Physiological Patterns using Optimal Transport Multi-Task Regression
Jiacheng Zhu,
Greg Darnell,
Agni Kumar,
Ding Zhao,
Bo Li,
XuanLong Nguyen,
Shirley You Ren.
PMLR Conference on Health, Inference, and Learning (CHIL), 2022
paper /
arXiv /
spotlight talk /
Apple Machine Learning Research
|
|
Accelerated Policy Evaluation: Learning Adversarial Environments with Adaptive Importance Sampling
Mengdi Xu,
Peide Huang,
Fengpei Li,
Jiacheng Zhu,
Xuewei Qi,
Kentaro Oguchi,
Zhiyuan Huang,
Henry Lam,
Ding Zhao.
IEEE International Conference on Intelligent Robots and Systems (IROS) 2022, shorter version on ICLR 2021 workshop
arXiv / ICLR 2021 Workshop
|
|
Context-Aware Safe Reinforcement Learning
for Non-Stationary Environments
Baiming Chen,
Zuxin Liu,
Jiacheng Zhu,
Mengdi Xu,
Wenhao Ding,
Ding Zhao.
IEEE International Conference on Robotics and Automation (ICRA), 2021
paper / arXiv
|
|
Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes
Mengdi Xu,
Wenhao Ding,
Jiacheng Zhu,
Zuxin Liu,
Baiming Chen,
Ding Zhao.
Conference on Neural Information Processing Systems (NeurIPS), 2020
paper / arXiv / code
|
|
Spatiotemporal Learning of Multivehicle Interaction Patterns in Lane-Change Scenarios
Chengyuan Zhang,
Jiacheng Zhu,
Wenshuo Wang,
Junqiang Xi.
IEEE Transactions on Intelligent Transportation Systems (ITS), 2021
paper / arXiv / project / shorter vision on ITSC 2019
|
|
Recurrent Attentive Neural Process for Sequential Data
Shenghao Qin*
Jiacheng Zhu*,
Jimmy Qin,
Wenshuo Wang,
Ding Zhao.
LIRE Workshop NeurIPS, 2019
arXiv / code / talk
|
|
A Tempt to Unify Heterogeneous Driving Databases using Traffic Primitive
Jiacheng Zhu,
Wenshuo Wang,
Ding Zhao.
The 24th IEEE International Conference on Intelligent Transportation Systems ITSC, 2018
paper / arXiv / online data platform
|
Service
- Reviewer: TMLR, TPAMI, ICLR (2022 - ), NeurIPS (2021 - ), ICML (2021 - ), AAAI 2023, CHIL (2022 - ), ML4H (2023 -), MLHC 2022, Transactions on ITS, ITSC
|
|