Ph.D. (Iowa State University)
Assistant Professor
Optimization, Machine Learning, Data Science, and Artificial Intelligence
Biography
Songtao Lu received his Ph.D. from the Department of Electrical and Computer Engineering at Iowa State University in 2018 and subsequently served as a Postdoctoral Associate in the same department at the University of Minnesota Twin Cities from 2018 to 2019. He then joined the IBM Thomas J. Watson Research Center in Yorktown Heights, where he worked as a Senior Research Scientist in the Mathematics and Theoretical Computer Science Department, while also serving as a Principal Investigator affiliated with the MIT-IBM Watson AI Lab in Cambridge.
Dr. Lu has received several prestigious awards, including the IBM Pat Goldberg Memorial Best Paper Honorable Mention Award (2023) as first author, the IBM Outstanding Innovation Award (2023), the IBM Entrepreneur Award (2023), the Best Paper Runner-Up Award at UAI (2022) as co-first author, the Outstanding Paper Award at FL-NeurIPS (2022), and Travel Awards for ICML (2019) and AISTATS (2017). He was also selected for Stanford University’s World’s Top 2% Scientists List (2024). Additionally, Dr. Lu has served as an Area Chair for ICML (2025) and NeurIPS (2023, 2024), and as a Senior Area Chair for AAAI (2024, 2025). He is a Senior Member of IEEE and a member of ACM.
- Songtao Lu, Siliang Zeng, Xiaodong Cui, Mark S. Squillante, Lior Horesh, Brian Kingsbury, Jia Liu, Mingyi Hong: A Stochastic Linearized Augmented Lagrangian Method for Decentralized Bilevel Optimization, NeurIPS, 2022.
- Songtao Lu, Kaiqing Zhang, Tianyi Chen, Tamer Basar, Lior Horesh: Decentralized Policy Gradient Descent Ascent for Safe Multi-Agent Reinforcement Learning, AAAI, 2021.
- Songtao Lu, Meisam Razaviyayn, Bo Yang, Kejun Huang, Mingyi Hong: Finding Second-Order Stationary Points Efficiently in Smooth Nonconvex Linearly Constrained Optimization Problems, NeurIPS, 2020.
- Songtao Lu, Ioannis Tsaknakis, Mingyi Hong, Yongxin Chen: Hybrid Block Successive Approximation for One-Sided Non-Convex Min-Max Problems: Algorithms and Applications, IEEE Transactions on Signal Processing, 2020.
- Songtao Lu, Mingyi Hong, Zhengdao Wang: PA-GD: On the Convergence of Perturbed Alternating Gradient Descent to Second-Order Stationary Points for Structured Nonconvex Optimization, ICML, 2019.
- Songtao Lu, Yanna Ding, Lior Horesh, Jianxi Gao, Malik Magdon-Ismail: Epigraph Based Multilevel Optimization (EMO) for Enhancing Chain-of-Thought Reasoning Capabilities, ICASSP, 2025.
- Songtao Lu: SLM: A Smoothed First-Order Lagrangian Method for Structured Constrained Nonconvex Optimization, NeurIPS, 2023.
- Songtao Lu: Bilevel Optimization with Coupled Decision-Dependent Distributions, ICML, 2023.
- Songtao Lu: A Single-Loop Gradient Descent and Perturbed Ascent Algorithm for Nonconvex Functional Constrained Optimization, ICML, 2022.
- Songtao Lu, Jason Lee, Meisam Razaviyayn, Mingyi Hong: Linearized ADMM Converges to Second-Order Stationary Points for Non-Convex Problems, IEEE Transactions on Signal Processing, 2021.
- IBM Pat Goldberg Memorial Best Paper Award (Honorable Mention), 2023
- IBM Outstanding Innovation Award, 2023
- IBM Entrepreneur Award, 2023
- Best Paper Runner-Up Award of the 38th Conference on Uncertainty in Artificial Intelligence (UAI), 2022
- FL-NeurIPS Outstanding Paper Award, 2022