About Me (CV here)

I am a fifth-year PhD candidate in the Department of Statistics at Harvard University, advised by Dr. Morgane Austern. I am graciously supported by the NSF Graduate Research Fellowship. Broadly, I am interested in the intersection of mathematics with statistical methods, such as universality, free probability, theoretical machine learning, and random matrix theory. In June 2022, I completed my B.S. in Pure Mathematics and B.S. in Statistics at UCLA. This past Summer 2026, I was a Quantitative Research Intern at Virtu Financial.

Outside of research, I am interested in lots of different things! I love playing the guitar & piano, cooking, making pottery, shooting film photography, tea culture, playing chess, learning languages, and more. My favorite artists are the Beatles, the Smiths, Clairo, Nick Drake, Mac DeMarco, and Chopin.

I do private tutoring for both statistics and mathematics. Please feel free to reach out to me by email if you would like tutoring for courses in the Harvard Statistics department, or really anything involving mathematics or statistics. Also check out my Instagram page, Razi ba Riazi, for cool mathematics videos, PhD advice, and more!

Theorem of the Month, November 2026

The shortest equation involving only matrix multiplication that the two matrices \(A = \begin{pmatrix} 2 & 0 \\ 0 & 3 \end{pmatrix},\ \ \ B = \begin{pmatrix} 3 & 5 \\ 0 & 5 \end{pmatrix}\) satisfy is $AB^{10}A^2BA^2BA^{10} = B^2A^6B^2A^2BABABA^2B^2A^2BAB^2$.

Song of the Month, November 2026

Graveyard Theme (Vince Guaraldi): The entire Vince Guaraldi music for the Peanuts Holiday movies has been on repeat for me, and this song is actually one I only recently came to appreciate. Be sure to listen to the (many) reprises of it too!

Publications

Esmaili Mallory, M.*, Huang, K. H.*, & Austern, M. (2025). “Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation.” In Proceedings of Thirty Eighth Conference on Learning Theory (pp. 1799–1918). PMLR.

Esmaili Mallory, M., Brown, J. & Glickman, M. (2026). “Analysis of Popular Songs Through Statistical Embeddings.” arXiv:2604.22925. Accepted to Journal of Data Science. Presented at Joint Statistical Meetings 2025.

Yu, A., Becquey, C., Halikias, D., Esmaili Mallory, M., & Townsend, A. (2021). “Arbitrary-Depth Universal Approximation Theorems for Operator Neural Networks.” arXiv preprint. arXiv:2109.11354.

(* indicates equal contribution)

Teaching

• Stat 175: Statistics and Data Science of Networks, Dr. Morgane Austern. Harvard University, Spring 2026.

• Stat 149: Introduction to Generalized Linear Models, Dr. Mark Glickman. Harvard University, Spring 2024.

• Stat 104: Introduction to Quantitative Methods for Economics, Dr. Kevin Rader. Harvard University, Fall 2023.

• Math 115A: Linear Algebra, Dr. Will Conley. UCLA, Winter 2022.

• Math 115A: Linear Algebra, Dr. Christy Hazel. UCLA, Spring 2021.

Talks & Presentations

• Stat 300: Research in Statistics Seminar. Harvard University, April 2025.

• Conference on Learning Theory (COLT) 2025. Lyon, France, July 2025.

• Princeton Machine Learning Theory Summer School. Princeton, NJ, August 2025.

• Joint Symposium on Statistics, Applied Math & Beyond. Harvard University, March 2026.

• Stat 300: Research in Statistics Seminar. Harvard University, April 2026.

• Joint Statistical Meetings (JSM) 2026. Boston, MA, August 2026.