CFAR
  • About A*STAR CFAR
    • Vision & Mission
    • Director's Message
    • Management
    • Our Team
  • Research
    • Research Pillars
      • AI for Science
      • Theory and Optimisation in AI
      • Artificial General Intelligence
      • Sustainable AI
      • Resilient & Safe AI
    • Participations
    • Publications
  • Talent
    • Career
    • Internship
    • Scholarship
    • Affiliated PhD students
    • Alumni
  • News
  • Events
    • Talks
    • Past Talks
    • 2024 IEEE Conference on Artificial Intelligence
  • Contact
  • Home
  • A*STAR CFAR
  • News
  • Features
  • A*STAR CFAR
  • About A*STAR CFAR
    • Vision & Mission
    • Director's Message
    • Management
    • Our Team
  • Research
    • Research Pillars
      • AI for Science
      • Theory and Optimisation in AI
      • Artificial General Intelligence
      • Sustainable AI
      • Resilient & Safe AI
    • Participations
    • Publications
  • Talent
    • Career
    • Internship
    • Scholarship
    • Affiliated PhD students
    • Alumni
  • News
  • Events
    • Talks
    • Past Talks
    • 2024 IEEE Conference on Artificial Intelligence
  • Contact
Agency for Science, Technology and Research (A*STAR)
PartnershipsCareersSuppliersContact UsWhistleblowing
  • Report Vulnerability
  • Privacy Statement
  • Terms & Conditions
  • Features

    Paper Acceptance at AISTATS 2025

    26 May 2025
    • Whatsapp
    • Telegram
    • Facebook
    • Twitter
    • Email
    • Linked In

    Held on 3 – 5 May at Phuket, Thailand, the 28th International Conference on Artificial Intelligence and Statistics (AISTATS) is an interdisciplinary gathering of researchers at the intersection of computer science, artificial intelligence, machine learning, statistics, and related areas.

    Congratulations to Dr Atsushi Nitanda, Principal Scientist from A*STAR Centre for Frontier AI Research (A*STAR CFAR) on having his paper accepted at AISTATS 2025. His paper titled “Clustered Invariant Risk Minimisation” extends the problem settings of Invariant Risk Minimisation (IRM) for Out-of-Distribution generalisation problems to unknown clustered environments settings. In such scenarios, where a given set of environments exhibits an unknown clustered structure, Dr Nitanda’s team aims to identify a single invariant feature extractor and per-cluster regressors (or classifiers) built on top of the feature extractor.

    More information on AISTATS 2025.