Bamdad Hosseini
Bamdad Hosseini is an applied mathematician whose work connects machine learning with Bayesian inverse problems and uncertainty quantification. He studied mechanical engineering at Sharif University of Technology before moving into applied mathematics at Simon Fraser, where his doctoral research focused on Bayesian inverse problems under John Stockie and Nilima Nigam. He joined Caltech as a postdoctoral fellow in 2018, received the NSERC Postdoctoral Fellowship and the Canadian Governor General's Academic Gold Medal in 2018, and joined the University of Washington in 2021. He developed neural-network and Gaussian-process methods for partial differential equations, kernel methods for operator learning, and analysis of generative priors; he also advised doctoral research on transport-based generative models. As of October 2026, he is an Associate Professor and Reeves Family Faculty Fellow in UW's Department of Applied Mathematics.
- Now at
- University of Washington
- Works
- 60
- Citations
- 897
- h-index
- 14
Publication numbers from OpenAlex, as of 27 October 2026.
Timeline
-
2011
Applied mathematics at Simon Fraser
In 2011, he begins an MSc in Applied and Computational Mathematics at Simon Fraser University after studying mechanical engineering at Sharif University of Technology. His master's thesis uses CLAWPACK to build a three-dimensional model of atmospheric pollutant dispersion.
-
2013
Bayesian inverse problems at SFU
In 2013, he begins doctoral research in Bayesian inverse problems at Simon Fraser, with John Stockie and Nilima Nigam as supervisors. His thesis work addresses computational and theoretical aspects of the field.
-
2018
Caltech appointments and awards
In 2018, he joins Caltech as a postdoctoral fellow. He receives an NSERC Postdoctoral Fellowship and the Canadian Governor General's Academic Gold Medal in 2018. At Caltech, he also serves as a von Karman instructor and senior postdoctoral fellow.
-
2020
Neural networks for parametric PDEs
In 2020, he coauthors Model Reduction and Neural Networks for Parametric PDEs with Kaushik Bhattacharya, Nikola B. Kovachki and Andrew M. Stuart. The framework combines neural networks with model reduction to approximate input-output maps between infinite-dimensional spaces.
-
2021
Gaussian processes for nonlinear PDEs
In October 2021, he joins the University of Washington's Department of Applied Mathematics as an assistant professor. He and Yifan Chen, Houman Owhadi and Andrew M. Stuart publish a Gaussian-process framework in 2021 for solving nonlinear PDEs and identifying unknown parameters in inverse problems.
-
2022
Bayesian inference and optimal transport
In 2022, he explains how machine-learning methods can construct data-driven priors within Bayesian inference and explores the methods through optimal transport.
-
2023
Kernel methods for operator learning
In 2023, he coauthors Kernel Methods are Competitive for Operator Learning with Pau Batlle, Matthieu Darcy and Houman Owhadi. The paper gives a kernel-based framework for learning operators between Banach spaces, with error analysis and numerical comparisons against neural-network methods.
-
2025
A dissertation on generative models
In 2025, he advises Biraj Pandey's PhD dissertation, Weaving Order From Uncertainty: Design, Analysis, and Application of Transport-based Generative Models.
-
2026
Generative priors and measure transport
In 2026, he and Ziqi Huang publish Error Analysis of Bayesian Inverse Problems with Generative Priors, which derives error bounds for generative priors in inverse problems. He also coauthors Approximating Measures on Function Spaces: Transport and Truncation with Ricardo Baptista and Alexander W. Hsu, developing approximations for Bayesian inverse problems and generative modeling.
-
As of October 2026
Associate professor at UW
As of October 2026, he is an Associate Professor and Reeves Family Faculty Fellow in the University of Washington's Department of Applied Mathematics. He teaches computational data analysis and complex-systems courses in 2025 and 2026 while researching machine-learning theory and uncertainty quantification.
Career
- NowUniversity of WashingtonAssociate Professor and Reeves Family Faculty Fellow
- From 2021University of WashingtonAssistant Professor
- From 2018California Institute of TechnologyPostdoctoral Fellow
- California Institute of TechnologyVon Karman Instructor and Senior Postdoctoral Fellow
Education
- From 2013Simon Fraser UniversityPhD
- From 2011Simon Fraser UniversityMSc in Applied and Computational Mathematics
- Sharif University of Technology
Sources and credits
Photo: We have no published photo of Bamdad Hosseini yet. Send us a free-licensed photo.
- Bayes' Rule and the Sound of Rain
- Bamdad Hosseini - Department of Mathematics - Simon Fraser University
- Natural Sciences Division Welcomes 12 New Faculty Members
- Model Reduction and Neural Networks for Parametric PDEs
- Solving and Learning Nonlinear PDEs with Gaussian Processes
- Kernel Methods are Competitive for Operator Learning
- Graduation 2025
- Error Analysis of Bayesian Inverse Problems with Generative Priors
- Approximating Measures on Function Spaces: Transport and Truncation
- Bamdad Hosseini | Department of Applied Mathematics | University of Washington
- Bamdad Hosseini

