Nguyen Duc Hoan

Johann Radon Institute, Linz, Austria | Phone: +43 677 6373 4511 | Email: [email protected]

Website: hoannguyen92.github.io

Professional Summary

Nguyen Duc Hoan is a postdoctoral researcher at the Johann Radon Institute (RICAM), part of the Austrian Academy of Sciences. He has a strong background in machine learning, domain adaptation, and inverse problems. With years of research experience in Austria and France, he has made significant contributions to projects on statistical learning and optimization. He has also published numerous works in prestigious conferences and journals in the field. Duc Hoan is always seeking opportunities to expand his knowledge and apply cutting-edge technologies to solve real-world problems.

Education

• Ph.D., Johannes Kepler University, Linz, Austria (2020 - 2023)

• Master's in ACSYON, University of Limoges, France (2016 - 2017)

• Bachelor's in Mathematics, University of Science, Vietnam (2010 - 2014)

Work Experience

• Postdoctoral Researcher, RICAM, Austria (2024 - Present)

  Nguyen Duc Hoan is conducting research on domain adaptation and machine learning at the RICAM institute.

• Ph.D. Candidate, RICAM, Austria (2020 - 2023)

  Worked on a thesis focusing on regularization in reproducing kernel Hilbert spaces for domain adaptation, under the supervision of leading professors.

• Lecturer, Thang Long University, Vietnam (2018 - 2020)

  Taught courses and participated in research projects on artificial intelligence and machine learning.

Research Projects

• Dermatological Fungal Disease Detection using Machine Learning (2019 - 2020)

  Collected and processed image data, built classification models for dermatological fungal diseases in France and Vietnam.

• Hanoi Formal Abstract Project (2018 - 2020)

  Collaborated with international universities to formalize mathematical theorems in Lean.

Publications

• Nguyen D. H., Zellinger W., Pereverzyev S., On regularized Radon-Nikodym differentiation, Journal of Machine Learning Research, 2024.

• Addressing parameter choice issues in unsupervised domain adaptation by aggregation, ICLR 2023 (Top 5%).

• On a regularization of unsupervised domain adaptation in RKHS, Applied and Computational Harmonic Analysis, 2022.

Contact

For more information, please contact via email: [email protected] or phone: +43 677 6373 4511