Qi Lei (雷琦)
 |
Assistant Professor of Mathematics and Data Science, and, by courtesy, Email: ql518 at nyu.edu |
Research Overview
My research interests are machine learning, deep learning, and optimization. Specifically, I am interested in developing sample- and computationally efficient algorithms for some fundamental machine learning problems.
(Curriculum Vitae, Github, Google Scholar)
Advertisement
I am actively looking for self-motivated and proactive students to work with. You are welcome to shoot me an email with your CV and short research plans/interests. (You may refer to this link to see whether our research interests match.)
For Ph.D. applicants, please apply to Courant Mathematics or Center for Data Science whichever you see fit and mention my name in your application. I do not plan to admit students from Courant CS for now.
For prospective students or interns who want to work with me in short term, please fill out this form so that we could find a suitable project for you.
For prospective post-doc applicants, I encourage you to apply for the positions of CDS Faculty Fellows, Courant Instructors, and Flatiron Research Fellows.
News and Announcement
10/2023 I am a co-PI on the ROME: Reduced Modeling with Extreme Data project, a Department of Energy project developing Science Foundations for Energy Earthshots. More information is in the DOE press release.
10/2023 Two papers (1 main + 1 findings) accepted at EMNLP 2023:
Jianwei Li, Qi Lei, Wei Cheng, Dongkuan Xu. ‘‘Towards Robust Pruning: An Adaptive Knowledge-Retention Pruning Strategy for Language Models"
Jianwei Li, Weizhi Gao, Qi Lei, Dongkuan Xu. ‘‘Breaking through Deterministic Barriers: Randomized Pruning Mask Generation and Selection"
09/2023 Two papers accepted at Neurips 2023:
Yijun Dong, Kevin Miller, Qi Lei, Rachel Ward. ‘‘Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clustering"
Qian Yu, Yining Wang, Baihe Huang, Qi Lei, Jason D. Lee. ‘‘Sample Complexity for Quadratic Bandits: Hessian Dependent Bounds and Optimal Algorithms"
08/2023 Won the Whitehead Fellowship for Junior Faculty in Biomedical and Biological Sciences
06/2023 New papers out:
Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clustering
Sample Complexity for Quadratic Bandits: Hessian Dependent Bounds and Optimal Algorithms
04/2023 Paper accepted at ICML 2023:
Tianci Liu, Tong Yang, Quan Zhang, Qi Lei. ‘‘Optimization for Amortized Inverse Problems"
04/2023 Won the NYU Research Catalyst Prize jointly with Zhengyuan Zhou
01/2023 Four papers accepted at AISTATS 2023:
Zihan Wang, Jason Lee, Qi Lei. ‘‘Reconstructing Training Data from Model Gradient, Provably"
Shuo Yang, Yijun Dong, Rachel Ward, Inderjit Dhillon, Sujay Sanghavi, Qi Lei. ‘‘Sample Efficiency of Data Augmentation Consistency Regularization"
Kurtland Chua, Qi Lei, Jason Lee. ‘‘Provable Hierarchy-Based Meta-Reinforcement Learning"
Qian Yu, Yining Wang, Baihe Huang, Qi Lei, Jason Lee. ‘‘Optimal Sample Complexity Bounds for Non-convex Optimization under Kurdyka-Lojasiewicz Condition"
01/2023 Invited talk at SLowDNN on reconstruction attack with guarantees
12/2022 Organized the workshop on meta-learning at NeurIPS 2022
09/2022 Presented the a unified view on reconstruction-based and similarity-based self-supervised learning in SIAM-MDS
09/2022 Started a new journey as an assistant professor of Courant Math/CDS at NYU!
Selected Papers
7. Zihan Wang, Jason Lee, Qi Lei. “Reconstructing Training Data from Model Gradient, Provably”, AISTATS 2023
6. Baihe Huang*, Kaixuan Huang*, Sham M. Kakade*, Jason D. Lee*, Qi Lei*, Runzhe Wang*, and Jiaqi Yang*. “Optimal Gradient-based Algorithms for Non-concave Bandit Optimization”, NeurIPS 2021
5. Jason D. Lee*, Qi Lei*, Nikunj Saunshi*, Jiacheng Zhuo*. “Predicting What You Already Know Helps: Provable Self-Supervised Learning”, NeurIPS 2021
4. Simon S. Du*, Wei Hu*, Sham M. Kakade*, Jason D. Lee*, Qi Lei*. “Few-Shot Learning via Learning the Representation, Provably”, The International Conference on Learning Representations (ICLR) 2021
3. Qi Lei, Jason D. Lee, Alexandros G. Dimakis, Constantinos Daskalakis. “SGD Learns One-Layer Networks in WGANs”, Proc. of International Conference of Machine Learning (ICML) 2020
2. Qi Lei*, Lingfei Wu*, Pin-Yu Chen, Alexandros G. Dimakis, Inderjit S. Dhillon, Michael Witbrock. “Discrete Adversarial Attacks and Submodular Optimization with Applications to Text Classification”, Systems and Machine Learning (sysML). 2019 (code, slides)
Press coverage: <Nature Story> <Vecturebeat> <Tech Talks> <机器之心>
1. Rashish Tandon, Qi Lei, Alexandros G. Dimakis, Nikos Karampatziakis, “Gradient Coding: Avoiding Stragglers in Distributed Learning”, Proc. of International Conference of Machine Learning (ICML), 2017 (code)