Scholar
Sarah Liaw
Google Scholar ID: 4sjEdTMAAAAJ
California Institute of Technology
Citations & Impact
Citations
1
H-index
1
i10-index
0
Publications
4
Co-authors
5
list available
Publications
Resume (English only)
Background
- Senior at Caltech majoring in Computer Science, with minors in Mathematics and Information + Data Science.
- Research interests focus on using computational mathematics to create more structured and physically grounded systems by integrating physical principles, especially for solving complex engineering problems.
- Aims to develop interpretable and physically informed models and algorithms for high-dimensional, stochastic, and non-convex systems, particularly where standard numerical methods fail.
- Key research questions: (1) How to build “good” models—uncertainty-aware, distributionally robust, with provable guarantees—from data in data-scarce environments; (2) How to quantify uncertainty in chaotic systems and tasks involving complex geometric representations.
- Recently exploring the intersection of statistical physics and machine learning by analyzing the learning process as a dynamical system.
- Currently working on cautious learning of agentic systems in out-of-distribution settings.
