About me

  • Associate Professor at the Institute of Statistical Mathematics (ISM)
    Department of Advanced Data Science
  • Associate Professor at the Graduate University for Advanced Studies (SOKENDAI)
    School of Multidisciplinary Sciences, Department of Statistical Science
  • Specially Appointed Associate Professor at Tohoku University (under JST BOOST program)
    Center for Language AI Research (CLAIR)
  • Visiting Researcher at OIST
    Machine Learning and Data Science (MLDS) Unit
  • bao.han (#) ism.ac.jp
  • Office: D410B (ISM)
  • CV, Google Scholar, DBLP, ORCID, researchmap, GitHub

    • Research interests

    My central focus of research is in theoretical understanding of statistical machine learning, particularly from the following perspectives.

    1. Learning theory of loss functions: Loss functions are interesting because they characterize a large portion of task properties such as adversarial robustness (COLT2020) and imbalancedness (AISTATS2020, AISTATS2021). Some task properties can be attained simultaneously by proper losses (COLT2023).
    2. Evaluation metrics of predictions and representations. Recently, I am interested in how it is possible to learn good representations via similarity in light of a downstream task (ICML2018, AISTATS2022, ICML2022).

    You may have a look at the slides of my past (and slightly outdated…) talks such as this to see my tastes.

    News

    🔎 For students

    If you are interested in PhD course at my place, please contact me directly first. I can take in a few PhD students via Statistical Science Course of SOKENDAI (and students will be based in ISM.)

    (archived)

    Upcoming travels

    • Aug 28-29: Sapporo (KAKENHI meeting)
    • Nov 12-15: Okinawa (IBIS)

    (archived)