Yanjun Han

I'm a Norbert Wiener postdoctoral associate at the Statistics and Data Science Center (SDSC) in MIT IDSS. My research interests lie in statistical machine learning, high-dimensional and nonparametric statistics, online learning and bandits, and information theory. I received my Ph.D. in Electrical Engineering from Stanford University in Aug 2021, under the supervision of Tsachy Weissman. In 2021-22, I was a postdoctoral scholar at the Simons Institute for the Theory of Computing, University of California, Berkeley. Prior to that, I received my B.E. in Electronic Engineering from Tsinghua University in Jul 2015. Future news: Starting from Sept 2023, I will be an Assistant Professor of Mathematics and Data Science at the Courant Institute of Mathematical Sciences and the Center for Data Science, NYU.

Recent papers

• Nived Rajaraman, Yanjun Han, Jiantao Jiao, Kannan Ramchandran, “Beyond UCB: Statistical Complexity and Optimal Algorithm for Non-linear Ridge Bandits”, in preparation.

• Ishaq Aden-Ali, Yanjun Han*, Jelani Nelson, Huacheng Yu, “On the amortized complexity of approximate counting”, Nov 2022.

• Wei Zhang, Yanjun Han, Zhengyuan Zhou, Aaron Flores, Tsachy Weissman, “Leveraging the Hints: Adaptive Bidding in Repeated First-Price Auctions”, NeurIPS, Nov 2022 (Spotlight).

• Yifei Wang, Tavor Baharav, Yanjun Han, Jiantao Jiao, David Tse, “Beyond the Best: Estimating Distribution Functionals in Infinite-Armed Bandits”, NeurIPS, Nov 2022.

• Nika Haghtalab, Yanjun Han*, Abhishek Shetty, Kunhe Yang, “Oracle-Efficient Online Learning for Beyond Worst-Case Adversaries”, NeurIPS, Nov 2022 (Designated as Oral).

• Brian Axelrod, Shivam Garg, Yanjun Han*, Vatsal Sharan, Gregory Valiant, “On the Statistical Complexity of Sample Amplification”, Jan 2022.

Contact

Email: yjhan [at] {stanford, berkeley, mit} [dot] edu (last one preferred for now)

E17-481A, IDSS, MIT
50 Ames St
Cambridge, MA 02142