Email: litian@uchicago.edu
Office: JCL 211


        


Tian Li


I am an Assistant Professor at the Computer Science Department and the Data Science Institute at the University of Chicago.

My research generally centers around large-scale machine learning and optimization. Specific topics include:

  • Efficient distributed training with applications to LLM optimization and federated learning (FedProx, FedDANE, Ditto, TailOPT)

  • Risk-averse or risk-seeking learning with applications to fairness and robustness (q-FFL, TERM)

  • Privacy-preserving machine learning (AdaDPS, DP^2)

I am particularly interested in designing, analyzing, and evaluating principled learning algorithms, modeling practical assumptions (e.g., communication constraints and heterogeneity) to address the above issues, as well as their interplays.

I am always looking for strong and motivated undergraduate and graduate students and postdocs. For Ph.D. applicants, please apply through the CS PhD program and/or the DS PhD program, and mention my name in your application(s).

News

2025: Teaching CMSC 35401: Topics in Machine Learning: Distributed and Federated Learning in Spring 2025.
2025: Multiple works will be presented at the ICLR main conference (many-objective optimization) and workshops (optimization under heavy-tailed noise and private RAG).
2025: Invited to serve on an NSF panel and as jury member for the Composite Learning Challenge by Germany's Federal Agency for Disruptive Innovation.
2025: Selected into AAAI New Faculty Highlights 2025 and gave a talk at AAAI.
2025: Serving as a Publication Co-Chair for MLSys 2025.
2024-2025: Gave talks on tilted losses at TTIC, CAM, UBC, and SFU.
2024: Cloud credit support from the NAIRR Pilot program.
2024: New preprint on tilted sharpness-aware minimization, where we explore a soft and smoothed version of SAM.
2024: Teaching CMSC 25300/35300: Mathematical Foundations of Machine Learning in 2024 Fall.
        

PhD Students

        

Research

Selected
All

Manuscripts

Efficient Distributed Optimization under Heavy-Tailed Noise
Su Hyeong Lee, Manzil Zaheer, Tian Li
[Arxiv]
Reweighting Local Mimina with Tilted SAM
Tian Li, Tianyi Zhou, Jeffrey Bilmes
[Arxiv]
Efficient Adaptive Federated Optimization
Su Hyeong Lee, Sidharth Sharma, Manzil Zaheer, Tian Li
[Arxiv]
Generalization Error of the Tilted Empirical Risk
Gholamali Aminian, Amir R. Asadi, Tian Li, Ahmad Beirami, Gesine Reinert, Samuel N. Cohen
[Arxiv]
A Field Guide to Federated Optimization
(50+ authors) Jianyu Wang, Zachary Charles, Zheng Xu, Gauri Joshi, H. Brendan McMahan, ..., Tian Li, ..., Virginia Smith, ...
[Arxiv]

Publications

Many-Objective Multi-Solution Transport
Ziyue Li, Tian Li, Virginia Smith, Jeff Bilmes, Tianyi Zhou
ICLR 2025
[Arxiv]
Maximizing Global Model Appeal in Federated Learning
Yae Jee Cho, Divyansh Jhunjhunwala, Tian Li, Virginia Smith, Gauri Joshi
TMLR 2024
[Paper] [Arxiv]
On Tilted Losses in Machine Learning: Theory and Applications
Tian Li*, Ahmad Beirami*, Maziar Sanjabi, Virginia Smith
JMLR 2023
[Paper] [Arxiv] [Code] [Poster] [Blog post]
Differentially Private Adaptive Optimization with Delayed Preconditioners
Tian Li, Manzil Zaheer, Ken Ziyu Liu, Sashank Reddi, Brendan McMahan, Virginia Smith
ICLR 2023
[Arxiv] [Code]
Private Adaptive Optimization with Side Information
Tian Li, Manzil Zaheer, Sashank Reddi, Virginia Smith
ICML 2022
[Paper] [Arxiv] [Code] [Slides] [Poster]
Motley: Benchmarking Heterogeneity and Personalization in Federated Learning
Shanshan Wu, Tian Li, Zachary Charles, Yu Xiao, Ziyu Liu, Zheng Xu, Virginia Smith
Federated Learning Workshop, NeurIPS 2022
[Arxiv] [Code]
Diverse Client Selection for Federated Learning via Submodular Maximization
Ravikumar Balakrishnan*, Tian Li*, Tianyi Zhou*, Nageen Himayat, Virginia Smith, Jeff Bilmes
ICLR 2022
[Paper]
Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing
Mikhail Khodak, Renbo Tu, Tian Li, Liam Li, Maria-Florina Balcan, Virginia Smith, Ameet Talwalkar
NeurIPS 2021
[Paper] [Arxiv] [Code]
Tilted Empirical Risk Minimization
Tian Li*, Ahmad Beirami*, Maziar Sanjabi, Virginia Smith
ICLR 2021
[Paper] [Arxiv] [Code] [Slides] [Poster] [Blog post]
Ditto: Fair and Robust Federated Learning Through Personalization
Tian Li, Shengyuan Hu, Ahmad Beirami, Virginia Smith
ICML 2021
Best Paper Award at ICLR 2021 Secure ML Workshop
[Paper] [Arxiv] [Code] [Slides] [Poster] [Video] [Longer Talk]
Heterogeneity for the Win: One-Shot Federated Clustering
Don Kurian Dennis, Tian Li, Virginia Smith
ICML 2021
[Paper] [Arxiv]
Ease.ML: A Lifecycle Management System for MLDev and MLOps
(20 authors) ..., Tian Li, ..., Wentao Wu, Ce Zhang
CIDR 2021
[Paper] [Ce's talk]
Federated Optimization in Heterogeneous Networks
Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, Virginia Smith
MLSys 2020
[Paper] [Arxiv] [Code] [Slides] [Poster] [Video]
Fair Resource Allocation in Federated Learning
Tian Li, Maziar Sanjabi, Ahmad Beirami, Virginia Smith
ICLR 2020
[Paper] [Arxiv] [Code] [Slides] [Video]
Federated Learning: Challenges, Methods, and Future Directions
Tian Li, Anit Kumar Sahu, Ameet Talwalkar, Virginia Smith
IEEE Signal Processing Magazine, Special Issue on Distributed, Streaming Machine Learning, 2020
The Most Popular SPM Article of 2020   (Link)
[Paper] [Arxiv] [Blog post]
Learning Context-aware Policies from Multiple Smart Homes via Federated Multi-Task Learning
Tianlong Yu, Tian Li, Yuqiong Sun, Susanta Nanda, Virginia Smith, Vyas Sekar, Srinivasan Seshan
IoTDI 2020
[Paper]
FedDANE: A Federated Newton-Type Method
Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, Virginia Smith
Asilomar Conference on Signals, Systems and Computers 2019 (Invited Paper)
[Paper] [Arxiv] [Code]
LEAF: A Benchmark for Federated Settings
Sebastian Caldas, Sai Meher Karthik Duddu, Peter Wu, Tian Li, Jakub Konecny, H. Brendan McMahan, Virginia Smith, Ameet Talwalkar
Federated Learning Workshop, NeurIPS 2019
[Website] [Arxiv]

Ease.ml: Towards Multi-Tenant Resource Sharing for Machine Learning Workloads
Tian Li, Jie Zhong, Ji Liu, Wentao Wu, Ce Zhang
VLDB 2018
[Paper] [Arxiv]
CUTE: Query Knowledge Graphs by Tabular Examples
Zichen Wang*, Tian Li*, Yingxia Shao, Bin Cui
WAIM 2018 (demo)
[Paper] [Poster]
An Overreaction to the Broken Machine Learning Abstraction: The ease.ml Vision
Ce Zhang, Wentao Wu, Tian Li
HILDA Workshop, SIGMOD 2017
[Paper]

Teaching

CMSC 35401: Topics in Machine Learning: Distributed and Federated Learning, Spring 2025
CMSC 25300/35300: Mathematical Foundations of Machine Learning, Spring 2025
CMSC 25300/35300: Mathematical Foundations of Machine Learning, Fall 2024
        

Talks

Learning in Heterogeneous Networks: Optimization and Fairness
Federated Learning One World (FLOW) Seminar
[Video]
Fair and Robust Federated Learning Through Personalization
TrustML Young Scientists Seminar
[Video (the first half)]
        

© 2025 Tian Li.