Lianghao Cao

Lianghao Cao is a Research Fellow in the Department of Computing and Mathematical Sciences at the California Institute of Technology. His research bridges machine learning, uncertainty quantification, and computational materials science, with specialized focus on block copolymer self-assembly and Bayesian inverse problems.

Dr. Cao develops cutting-edge methodologies including neural operator acceleration, measure transport techniques, and likelihood-free inference for high-dimensional scientific challenges. His materials science work integrates physics-based models with machine learning surrogates to predict copolymer behavior, while his epidemiological research demonstrates cross-disciplinary application of continuum modeling. Key contributions span constitutive law learning, microphase separation theory, and scalable Bayesian inversion frameworks.

Analysis of his 2020-2025 publications reveals a clear trajectory toward efficient computational paradigms for infinite-dimensional inverse problems. His work increasingly emphasizes structure-exploiting algorithms like LazyDINO and derivative-informed MCMC, demonstrating how machine learning can overcome computational bottlenecks in materials modeling. The consistent application of Bayesian frameworks across domains highlights his unified approach to uncertainty quantification in complex systems.