I am a graduate student at the Operations Research Center at MIT, where I am fortunate to be advised by Vivek Farias and Retsef Levi.

Previously, I graduated from Cornell University with a B.A. in mathematics and computer science in May 2021. During my undergraduate years, I worked with various research advisors, including Prof. Adrian Lewis, James Renegar, Alex Townsend, and Christopher De Sa.

I am broadly interested in the mathematical foundations of machine learning, including optimization, numerical analysis, statistics, and geometric deep learning. More recently, I have been working on applications and interpretability of transformer models.

Email: qingxuan@mit.edu

Links: [Resume] [Github] [Google Scholar]

Conference Publications

1. Horace He, Aaron Lou*, Qingxuan Jiang*, Isay Katsman*, Serge Belongie, and Ser-Nam Lim, Adversarial Example Decomposition, International Conference on Machine Learning Workshop (ICMLW), Long Beach, CA, 2019. [arXiv]
2. Aaron Lou*, Isay Katsman*, Qingxuan Jiang*, Serge Belongie, Ser-Nam Lim, and Christopher De Sa, Differentiating through the Fréchet Mean, International Conference on Machine Learning (ICML), 2020. [Paper] [arXiv] [Code] [Video]
3. Aaron Lou*, Derek Lim*, Isay Katsman*, Leo Huang*, Qingxuan Jiang, Ser-Nam Lim, and Christopher De Sa, Neural Manifold Ordinary Differential Equations, Neural Information Processing Systems (NeurlPS), 2020. [Paper] [arXiv] [Code] [Video]

(* indicates equal contribution)

Journal Publications

1. Qingxuan Jiang, Tian Lan, Kasso Okoudjou, Robert Strichartz, Shashank Sule, Sreeram Venkat, Xiaoduo Wang, Sobolov Orthogonal Polynomials on the Sierpinski Gasket, Journal of Fourier Analysis and Applications 27.3 (2021): 1-38. [Paper] [arXiv] [Code]

(In alphabetical order)

Theses and Other Reports

1. Proximal Bundle Methods and Nonlinear Acceleration: An Exploration, undergraduate thesis advised by Professor Adrian Lewis. [Thesis] [Code]
2. First-order Methods on Large-scale Convex Optimization Problems, research project advised by Professor James Renegar. [Report] [Code]

Other Research Experiences

• Local Elasticity and Generalization of Neural Networks, Advised by Professor Weijie Su
• Analysis and Implementation of Spectral Method, Cornell REU 2020, Advised by Professor Alex Townsend. [Slide1] [Slide2]
• Orthogonal Polynomials on the Sierpinski Gasket, Cornell SPUR 2019, Advised by Professor Kasso Okoudjou and Robert Strichartz. [arXiv] [Website] [Code]

Teaching

I have been an undergraduate teaching assistant for the following courses at Cornell:

• CS 2800: Discrete Structures (SP18, FA18, SP19)
• CS 4820: Introduction to Analysis of Algorithms (FA19)
• CS 4850: Mathematics Foundations for the Information Age (SP20)
• CS 4780: Machine Learning for Intelligent Systems (FA20, SP21)

Honors and Awards

• Tanner Dean’s Scholars, Cornell University
• Rank 122 out of 4638, William Lowell Putnam Mathematical Competition 2017
• 4th Place, Cornell Mathematical Contest in Modeling 2018
• Honorable Mention, International Mathematical Contest in Modeling 2019

Activities

• Member, Cornell University Artificial Intelligence Research Group [Website]

Notes on Various Topics

• Class Notes on Kurdyka-Lojasiewicz Inequality in Optimization [Note]