Qi Lei

Qi Lei is an Assistant Professor in the Department of Computer Science at New York University. His research focuses on bridging the theoretical and empirical boundaries of modern machine learning algorithms, particularly in the areas of AI safety, data privacy, and distributionally robust algorithms. He is also affiliated with the Courant Institute of Mathematical Sciences and the Center for Data Science. His work includes topics such as data privacy, sample- and parameter-efficient learning, and the theoretical foundations of pre-trained models. He is a member of the CILVR lab and the Math and Data group. Additionally, he is a Google DeepMind Faculty member.

Qi Lei is an Assistant Professor of Mathematics and Data Science at New York University, specializing in Machine Learning, Optimization, and Deep Learning. Their research focuses on improving the efficiency and robustness of machine learning systems through advanced optimization techniques and theoretical analysis. Key areas include distributed learning, self-supervised learning, adversarial training, and robustness to adversaries. They have explored gradient coding to mitigate stragglers in distributed settings and developed methods for stabilizing gradients in deep neural networks. Additionally, their work addresses time-series embedding, label propagation, and in-context learning, emphasizing theoretical guarantees and practical applications.