SUZUKI, Atsushi
Scholar

SUZUKI, Atsushi

Google Scholar ID: kbMr45UAAAAJ
Assistant Professor, The University of Hong Kong
learning theorymachine learningdifferential geometrystatisticsinformation theory
Citations & Impact
All-time
Citations
77
 
H-index
6
 
i10-index
3
 
Publications
15
 
Co-authors
0
 
Publications
15 items
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
  • Publications: 'Hallucinations are inevitable but statistically negligible' (2025-02-15) and 'Foundation of Calculating Normalized Maximum Likelihood for Continuous Probability Models' (2024-09-12). Awards: NeurIPS 2023 Complimentary Registration (awarded for top 8% reviewers). Academic Services: Area Chair for NeurIPS 2024, Session Chair for IJCAI 2023, Topic Editor for Frontiers in Big Data, and Reviewer for JMLR, ICML, NeurIPS, ICLR, etc.
Research Experience
  • 2025.01-Present: Assistant Professor, Department of Mathematics, Faculty of Sciences, The University of Hong Kong, Hong Kong SAR; 2022.08-2024.12: Assistant Professor (UK Lecturer), Department of Informatics, Faculty of Natural, Mathematics & Engineering Sciences, King's College London, United Kingdom; 2023.05-2024.03: Visiting Researcher, Department of Mathematical Informatics, Graduate School of Information Science and Technology, The University of Tokyo, Japan; 2020.04-2022.08: Assistant Professor (UK Lecturer), School of Computing and Mathematical Sciences, University of Greenwich, United Kingdom.
Education
  • 2020.03: Doctor of Information Science and Technology from The University of Tokyo, supervised by Professor Kenji Yamanishi; 2017.03: Master of Information Science and Technology from The University of Tokyo, supervised by Professor Kenji Yamanishi; 2015.03: Bachelor of Engineering from The University of Tokyo, supervised by Professor Shinji Hara.
Background
  • Research Interests: Applied Mathematics for Machine Learning, including Riemannian-manifold-based (including hyperbolic-space-based) machine learning and optimization, evaluating the limitations of machine learning through learning theory and information theory, and manipulating and understanding multi-media data (e.g., images, languages, audio, etc.) using deep learning, geometry, and algebra. Currently, an Assistant Professor at the Department of Mathematics, Faculty of Sciences, The University of Hong Kong.
Miscellany
  • Languages: Fluent in English, Native Japanese, Fluent in Mandarin, Others: Malay-Indonesian, Cantonese. Programming: C++11, Python 3, Ruby on Rails, Tensorflow 2, MATLAB, Perl.
Co-authors
0 total
Co-authors: 0 (list not available)