Honglin Yuan

Honglin Yuan has a work experience in various roles and companies. In 2020, they worked as a Research Intern at Google, where they co-authored a research paper on "Federated Composite Optimization" (ICML 2021) with Manzil Zaheer and Sashank Reddi. In 2021, they continued their research internship at Google and published another research paper on "What Do We Mean by Generalization in Federated Learning?" (ICLR 2022) with Warren Morningstar, Lin Ning, and Karan Singhal. Additionally, they held the position of Student Researcher during the same period. Currently, in 2022, Honglin is working as a Quantitative Researcher at Citadel Securities.

Honglin Yuan has a strong educational background in the field of computational and mathematical engineering. From 2017 to 2022, they pursued their Doctor of Philosophy (Ph.D.) at Stanford University. Prior to that, they completed their Bachelor of Science (B.S.) in Applied Mathematics from Peking University, where they studied from 2013 to 2017. Additionally, during their time at Peking University, Honglin Yuan also obtained a double degree in Computer Science, completing their second Bachelor of Science (B.S.) from 2014 to 2017.