Machine learning for material science

Machine learning has tremendous prediction to accelerate the design of novel materials. I currently collaborate with researchers at Princeton, the Colorado School of Mines, UIUC, and WashU on applications of machine learning and probabilistic methods to material science problems. We are developing new methods for active search, Markov Chain Monte Carlo simulation, and combinatorial design. Current application areas include machine learning for alloy design, ML-assisted property prediction, and topology optimization of structural materials.


Multi-fidelity Monte Carlo: a pseudo-marginal approach

Advances in Neural Information Processing Systems (NeurIPS), 2022

PDF arXiv

Diana Cai
Center for Computational Mathematics

I am broadly interested in machine learning and statistics, and in particular, developing robust and reliable methods for modeling and inference.