Han Bao

About me

Associate Professor at the Institute of Statistical Mathematics (ISM)

Associate Professor at the Graduate University for Advanced Studies (SOKENDAI)

Specially Appointed Associate Professor at Tohoku University (under JST BOOST program)

Visiting Researcher at OIST (MLDS Unit)

bao.han (#) ism.ac.jp

Office: D410B (ISM)

CV, Google Scholar, DBLP, ORCID, researchmap, GitHub

🔎 For students

I'm open for accepting PhD students and interns at ISM. Feel free to reach out to me. Here are some of my favorite recent papers, but I'm more broadly interested in learning theory.

Research interests

Learning theory
- classification-calibrated losses, proper scoring rule, property elicitation
- class probability estimation, probability calibration
- learning dynamics, gradient descent
- convex analysis
Representation learning
- contrastive learning
Online convex optimization

News

Mar 28, 2025: My grant proposal to JST-BOOST (Japanese govermental 5 year research funding for early-career researchers in AI field) has been accepted (official info).
Feb 25, 2025: I moved to the Institute of Statistical Mathematics as an associate professor.
Jan 23, 2025: Our three new papers are accepted by AISTATS2025: (1) unified understanding of online inverse optimization via Fenchel-Young loss, (2) non-principal-centric model of inverse optimization via prediction market, and (3) a new loss class extending proper loss to incorporate the focal loss. Additionally, our two papers are accepted by ICLR2025: (1) hippocampus-inspired self-supervised learning and (2) scheduled knowledge distillation for language modeling.
(archived)

Upcoming travels

Aug 28-29: Sapporo (KAKENHI meeting)
Nov 12-15: Okinawa (IBIS)
Dec 2-7: San Diego (NeurIPS, TBD)
(archived)