Experience of Mentoring

RPI-IBM AI Research Program

• Yanna Ding, Incomming Intern, (Ph.D. advisor: Jianxi Gao, Department of Computer Science)

• Hongkang Li, Intern, (Ph.D. advisor: Meng Wang, Department of Electrical, Computer and Systems Engineering)
  Training Nonlinear Transformers for Efficient In-Context Learning: A Theoretical Learning and Generalization Analysis
  Hongkang Li, Meng Wang, Songtao Lu, Xiaodong Cui, Pin-Yu Chen
  ICML, 2024.

• Quan Xiao, Intern, (Ph.D. advisor: Tianyi Chen, Department of Electrical, Computer and Systems Engineering)
  A Generalized Alternating Method for Bilevel Optimization under the Polyak-Łojasiewicz Condition
  Quan Xiao, Songtao Lu, Tianyi Chen
  NeurIPS, 2023.

• Han Shen, Intern, (Ph.D. advisor: Tianyi Chen, Department of Electrical, Computer and Systems Engineering)
  Distributed Offline Policy Optimization Over Batch Data
  Han Shen, Songtao Lu, Xiaodong Cui, Tianyi Chen
  AISTATS, 2023.

• Lisha Chen, RPI AI Scholar, (Ph.D. advisor: Tianyi Chen, Department of Electrical, Computer and Systems Engineering)
  Understanding Benign Overfitting in Gradient-based Meta Learning
  Lisha Chen, Songtao Lu, Tianyi Chen
  NeurIPS, 2022.

• Yonggui Yan, Intern, (Ph.D. advisor: Yangyang Xu, Department of Mathematical Sciences)
  Compressed Decentralized Proximal Stochastic Gradient Method for Nonconvex Composite Problems with Heterogeneous Data
  Yonggui Yan, Jie Chen, Pin-Yu Chen, Xiaodong Cui, Songtao Lu, Yangyang Xu (IBM authors: alphabetical order)
  ICML, 2023.

• Zichong Li, RPI AI Scholar, (Ph.D. advisor: Yangyang Xu, Department of Mathematical Sciences)
  Stochastic Inexact Augmented Lagrangian Method for Nonconvex Expectation Constrained Optimization
  Zichong Li, Pin-Yu Chen, Sijia Liu, Songtao Lu, Yangyang Xu (IBM authors: alphabetical order)
  Computational Optimization and Applications, vol. 87, pp. 117 - 147, 2024.
  Zeroth-Order Optimization for Composite Problems with Functional Constraints
  Zichong Li, Pin-Yu Chen, Sijia Liu, Songtao Lu, Yangyang Xu (IBM authors: alphabetical order)
  AAAI, 2022. (Oral Presentation)
  

  Rate-Improved Inexact Augmented Lagrangian Method for Constrained Nonconvex Optimization
  Zichong Li, Pin-Yu Chen*, Sijia Liu*, Songtao Lu*, Yangyang Xu* (* represents alphabetical order)
  AISTATS, 2021.

MIT-UROP – Undergraduate Research Opportunities Program

• Alex Gu, MIT undergraduate student
  Min-Max Multi-Objective Bilevel Optimization with Applications in Robust Machine Learning
  Alex Gu, Songtao Lu, Parikshit Ram, Tsui-Wei Weng
  ICLR, 2023.

NSF AI-EDGE

• Jayanth Reddy Regatti, Ph.D. student (Ph.D. advisors: Abhishek Gupta, Ness Shroff)
  Conditional Moment Alignment for Improved Generalization in Federated Learning
  Jayanth Reddy Regatti, Songtao Lu, Abhishek Gupta, Ness Shroff
  NeurIPS Workshop on Federated Learning (FL-NeurIPS), 2022.
  - Oral Presentation: 11% [12/103] and Outstanding Paper Award

• Zhuqing Liu, Ph.D. student (Ph.D. advisor: Jia (Kevin) Liu)
  PILOT: An O(1/K)-Convergent Approach for Policy Evaluation with Nonlinear Function Approximation
  Zhuqing Liu, Xin Zhang, Jia Liu, Zhengyuan Zhu, Songtao Lu
  ICLR, 2024. Spotlight Presentation
  PRECISION: Decentralized Constrained Min-Max Learning with Low Communication and Sample Complexities
  Zhuqing Liu, Xin Zhang, Songtao Lu, Jia Liu
  ACM Mobihoc, 2023.
  Prometheus: Taming Sample and Communication Complexities in Constrained Decentralized Stochastic Bilevel Learning
  Zhuqing Liu, Xin Zhang, Prashant Khanduri, Songtao Lu, Jia Liu
  ICML, 2023.
  Taming Communication and Sample Complexities in Decentralized Policy Evaluation for Cooperative Multi-Agent Reinforcement Learning
  Xin Zhang*, Zhuqing Liu*, Jia Liu, Zhengyuan Zhu, Songtao Lu
  NeurIPS, 2021.

• FNU Hairi, Ph.D. student (Ph.D. advisor: Jia (Kevin) Liu)

  Finite-Time Convergence and Sample Complexity of Multi-Agent Actor-Critic Reinforcement Learning with Average Reward
  FNU Hairi, Jia Liu, Songtao Lu
  ICLR, 2022. (Spotlight Presentation)