Houman Owhadi
Professor of Applied and Computational Mathematics and Control and Dynamical Systems
B.S., Ecole Polytechnique (France), 1994; M.S., Ecole Nationale des Ponts et Chaussees, 1997; Ph.D., Ecole Polytechnique Federale de Lausanne (Switzerland), 2001. Assistant Professor, Caltech, 2004-11; Professor, 2011-.
Research interests: statistical numerical approximation, numerical homogenization, operator adapted wavelets, fast solvers, Gaussian process regression, machine learning, multi-scale and stochastic analysis, stochastic mechanics and geometric integration, uncertainty quantification
Overview
Professor Owhadi's research concerns the exploration of interplays between numerical approximation, statistical inference and learning from a game theoretic perspective. Whereas the process of discovery is usually based on a combination of trial and error, insight and plain guesswork, his research is motivated by the facilitation/automation possibilities emerging from these interplays.
Publications
- Batlle, Pau;Chen, Yifan et al. (2025) Error analysis of kernel/GP methods for nonlinear and parametric PDEsJournal of Computational Physics
- Hamzi, Boumediene;Hutter, Marcus et al. (2024) Bridging Algorithmic Information Theory and Machine Learning: A new approach to kernel learningPhysica D: Nonlinear Phenomena
- Chen, Yifan;Owhadi, Houman et al. (2024) Sparse Cholesky Factorization for Solving Nonlinear PDEs via Gaussian Processes
- Owhadi, H. (2023) Gaussian process hydrodynamicsApplied Mathematics and Mechanics
- Hamzi, Boumediene;Owhadi, Houman et al. (2023) A note on microlocal kernel design for some slow–fast stochastic differential equations with critical transitions and application to EEG signalsPhysica A
- Darcy, Matthieu;Hamzi, Boumediene et al. (2023) One-shot learning of stochastic differential equations with data adapted kernelsPhysica D
- Owhadi, Houman (2023) Do ideas have shape? Idea registration as the continuous limit of artificial neural networksPhysica D
- Lee, Jonghyeon;De Brouwer, Edward et al. (2023) Learning dynamical systems from data: A simple cross-validation perspective, Part III: Irregularly-sampled time seriesPhysica D
- Akian, J.-L.;Bonnet, L. et al. (2022) Learning "best" kernels from data in Gaussian process regression. With application to aerodynamicsJournal of Computational Physics
- Smirnov, Alexandre;Hamzi, Boumediene et al. (2022) Mean-field limits of trained weights in deep learning: A dynamical systems perspectiveDolomites Research Notes on Approximation
Related Courses
2023-24
ACM 118 – Stochastic Processes and Regression
ACM/IDS 216 – Markov Chains, Discrete Stochastic Processes and Applications
2022-23
ACM 118 – Stochastic Processes and Regression
ACM/IDS 216 – Markov Chains, Discrete Stochastic Processes and Applications
2021-22
ACM 118 – Stochastic Processes and Regression
ACM/IDS 216 – Markov Chains, Discrete Stochastic Processes and Applications
2020-21
ACM 118 – Stochastic Processes and Regression
ACM/IDS 216 – Markov Chains, Discrete Stochastic Processes and Applications