Ankit Sonthalia

Ankit Sonthalia

PhD Student

Scalable Trustworthy AI

Biography

I’m a first-year PhD candidate in Seong Joon Oh’s group Scalable Trustworthy AI (STAI). Before this, I have meddled in various research activities during my undergraduate studies, an internship and my previous job as a research software engineer. Lately, I am interested in understanding how and why neural networks work (or don’t). The focus is on making discoveries that benefit use cases across the board. The long-term goal of my research is to inject principles of causality in AI. I will write more as my research interests become more concrete.

Would you like to share a cool idea? Do you need my help with something? Feel free to reach out over email or LinkedIn.

Interests
  • Trustworthy Machine Learning
  • Robustness
  • OOD Generalization
  • Causality in ML
  • Parameter Spaces
Education
  • M.Sc. Mathematics, 2022

    Birla Institute of Technology & Science (BITS), Pilani

  • B.E. Computer Science, 2022

    Birla Institute of Technology & Science (BITS), Pilani

Experience

 
 
 
 
 
PhD Student
March 2024 – Present Tübingen, Germany
 
 
 
 
 
Research Software Engineer
August 2022 – February 2024 Tübingen, Germany
 
 
 
 
 
Research Assistant
February 2022 – June 2022 Kaiserslautern, Germany

Recent Publications

(2024). Do Deep Neural Network Solutions Form a Star Domain?.

PDF Code