Bio

Agnideep “Agni” Aich is a Postdoctoral Scholar in the HEAL Lab within the Department of Emergency Medicine at Stanford University School of Medicine, under the mentorship of Dr. Christian Rose. His research develops statistical machine learning methods for understanding dependence, extremes, and risk in complex healthcare and biomedical data.

Agni completed his PhD in Mathematics with a concentration in Statistical Machine Learning. His doctoral research focused on learning from extremes by developing dependence-aware feature selection methods that rank predictors by their joint extreme behavior with clinical and public health outcomes.

Honors & Awards

  • J.D. Testerman Award (Outstanding PhD Student), Department of Mathematics, University of Louisiana at Lafayette (Spring 2025)
  • Rhodes Outstanding Teaching Assistant Award (Outstanding Teaching Performance), Department of Mathematics, University of Louisiana at Lafayette (Fall 2022)

Boards, Advisory Committees, Professional Organizations

  • Member, American Statistical Association (ASA) (2025 - Present)
  • Member, Institute of Mathematical Statistics (IMS) (2025 - Present)
  • Member, American Mathematical Society (AMS) (2025 - Present)
  • Member, Society for Industrial and Applied Mathematics (SIAM) (2025 - Present)

Professional Education

  • PhD, University of Louisiana at Lafayette, Statistical Machine Learning (2026)
  • MS, University of Louisiana at Lafayette, Mathematics (2021)
  • MS, University of Calcutta, Statistics (2018)
  • BS (with Hons.), University of Calcutta, Statistics (2016)

Stanford Advisors

Contact

  • Academic
    agnideep@stanford.edu
    University - Scholar Department: Emergency Medicine - Adult Clinical/Academic Position: Postdoctoral Scholar

Additional Info

Links

Current Research and Scholarly Interests

Agni's research develops interpretable statistical machine learning methods for clinical, biomedical, and population health data, with interests spanning dependence-aware learning and copula-based methods, extreme-event modeling, predictive modeling, supervised feature selection, and AI in healthcare. At the HEAL Lab, he analyzes clinical workflows and AI implementation to advance understanding of the human experience in healthcare, emphasizing practical, interpretable, human-centered outcomes.

Lab Affiliations