Debabrota Basu
Scholar

Debabrota Basu

Google Scholar ID: e26Maa4AAAAJ
Faculty, Inria at University of Lille and CNRS (CRIStAL), ELLIS Scholar
Reinforcement LearningMulti-armed BanditsDifferential PrivacyFairnessOptimization
Citations & Impact
All-time
Citations
892
 
H-index
16
 
i10-index
29
 
Publications
20
 
Co-authors
78
list available
Contact
Resume (English only)
Academic Achievements
  • Will be presenting multiple papers in 2025 at EWRL, AISTATS, AAAI, and PPAI conferences, covering topics such as preference-based pure exploration, privacy in high-dimensional bandits, endogeneity in online instrumental variable regression and bandits, using topological features for adversarial robustness, AFA: a universal, accurate, and efficient auditor of bias and risk, and pure exploration in bandits with linear constraints. Additionally, presenting works at NeurIPS 2024 and ICLR 2024.
Research Experience
  • Presently teaching postgraduate level courses on privacy, responsible machine learning, and research methods in AI at École normale supérieure-PSL University, Université de Lille, and Centrale Lille. Before arriving in Lille, he was a postdoctoral researcher at the Data Science and AI Division, Department of Computer Science and Engineering, Chalmers University of Technology.
Education
  • PhD in Computer Science from the Department of Computer Science, School of Computing, National University of Singapore, advised by Stéphane Bressan and Pierre Senellart; B.E. degree with Honours in Electronics and Telecommunication Engineering from the Department of Electronics and Telecommunication Engineering, Jadavpur University.
Background
  • Currently, a tenured faculty (ISFP) at the Scool team (previously called SequeL) of Inria Centre at University of Lille in France. Research aims to construct algorithms and systems for developing efficient, robust, private, and ethical learning machines that solve real-life problems. Methodologically, his work blends statistics, machine learning, and optimization. On the application side, he is interested in developing theoretically-grounded Responsible AI algorithms for sustainable agro-ecology, medical and pharmaceutical applications, energy-efficient and safe autonomous systems, and algorithmic audits.
Miscellany
  • Outside academia, writes poetry and plays, airs dissent through articles on scientific and social issues, and has acted in plays and cinema.