SCS Faculty Candidate

  • Remote Access Enabled
  • Virtual Presentation
  • Ph.D. Candidate
  • Computer Science Department
  • Stanford University

Machine Learning for Accelerating Scientific Discovery

The dramatic increase in both sensor capabilities and computational power over the last few decades has created enormous opportunities for using machine learning (ML) to enhance scientific discovery. To realize this potential, ML systems must seamlessly address the challenges of real-world scientific discovery.  In this talk, I'll focus on two challenges: How can we use ML to model high-dimensional data in the presence of uncertainty? How can we use such models to design time-intensive experiments under budget constraints? For both these questions, I’ll first discuss the key limitations of existing approaches through the lens of probabilistic reasoning. Next, I’ll present algorithms from my research that can effectively overcome these challenges. These algorithms are theoretically principled, domain-agnostic, and exhibit strong empirical performance. Notably, I’ll describe a collaboration with chemists and material scientists where we used these algorithms for efficiently and accurately optimizing the charging protocols for electric batteries. Finally, I'll conclude with a discussion on the broader significance of this research for science and engineering and an overview of future directions for using ML to accelerate scientific discovery.

Aditya Grover is a fifth-year Ph.D. candidate in Computer Science at Stanford University advised by Stefano Ermon. His research focuses on probabilistic modeling and reasoning in high dimensions and is grounded in applications in physical sciences. Aditya’s research has been published in top scientific and ML/AI venues (e.g., Nature, NeurIPS, ICML, ICLR, AAAI, AISTATS), included in widely-used open source ML software, and deployed into production at major technology companies. His work has been recognized with a best paper award (StarAI), a Lieberman Fellowship, a Data Science Institute Scholarship, and a Microsoft Research Ph.D. Fellowship. He is also a Teaching Fellow at Stanford since 2018, where he co-created and teaches a new class on Deep Generative Models. Previously, Aditya obtained his bachelors in Computer Science and Engineering from IIT Delhi in 2015, where he received a best undergraduate thesis award.

Faculty Host: Eric Poe Xing

Machine Learning Department

Zoom Participation Enabled. See announcement for registration details.

For More Information, Please Contact: