Papers and Presentations

Preprints

“Goal-oriented learning of stochastic differential equations using error bounds on path-space observables.”
Authors: Joanna Zou, Han Cheng Lie, Youssef Marzouk
Preprint, submitted to SIAM Journal on Multiscale Modeling and Simulation. 2026.

“Stein kernelized molecular dynamics for active learning of interatomic potentials.”
Authors: Joanna Zou, Fraser Birks, Dallas Foster, Youssef Marzouk
Preprint, submitted to NeurIPS. 2026.

Published Papers

“Data curation for machine learning interatomic potentials by determinantal point processes.”
Authors: Joanna Zou, Youssef Marzouk
ICLR AI4MAT Workshop. 2025.

“Virtual sensing of subsoil strain response in monopile-based offshore wind turbines via Gaussian process latent force models.”
Authors: Joanna Zou, Eliz-Mari Lourens, Alice Cicirello
Mechanical Systems & Signal Processing, 200 (110488). 2023.

“Gaussian process latent force models for virtual sensing in a monopile-based offshore wind turbine.”
Authors: Joanna Zou, Alice Cicirello, Alexandros Iliopoulos, Eliz-Mari Lourens
Proceedings of the European Workshop on Structural Health Monitoring. Lecture Notes in Civil Engineering, vol 253. Springer, Cham. 2022.

“Surrogate modeling for the seismic response estimation of residential wood frame structures.”
Authors: Joanna Zou, David P. Welch, Adam Zsarnoczay, Alexandros Taflanidis, Gregory Deierlein
Proceedings of the 17th World Conference in Earthquake Engineering. Sendai, Japan. 2020.

“Physics-informed analysis of patient-induced structural vibration data for monitoring gait health in individuals with muscular dystrophy.”
Authors: Yiwen Dong, Joanna Zou, Jingxiao Liu, Jonathan Fagert, Mostafa Mirshekari, Linda Lowes, Megan Iammarino, Pei Zhang, Hae Young Noh
Proceedings of the ACM International Joint Conference on Pervasive and Ubiquitous Computing. (525–531). 2020.

Theses

“Goal-Oriented Learning of Stochastic Dynamical Systems.”
Joanna Zou
PhD Thesis, Massachusetts Institute of Technology. 2026.

Working Papers (in progress)

J. Zou, H. C. Lie, Y. Marzouk. “Derivative-informed subspaces for dimension reduction on Hilbert spaces of drift functions of stochastic differential equations.”

J. Zou, L. Richter, Y. Marzouk. “Dimension reduction of learning objectives for stochastic optimal control and diffusion-based sampling.”

R. Alomairy, J. Zou. “Accelerated learning of machine learning force fields via mixed-precision Gaussian processes.”

Talks

“Dimension reduction on Hilbert spaces of drift functions of SDEs for the uncertainty quantification of path-space observables.”
SIAM Conference on Uncertainty Quantification (SIAM UQ). March 2026. Minneapolis, Minnesota.

“Goal-oriented learning of stochastic dynamical systems using error bounds on path-space observables.”
SIAM Conference on Applications of Dynamical Systems (SIAM DS). May 2025. Denver, Colorado.

“Path space error bounds for the statistical learning of SDEs.”
University of Potsdam, Institute for Mathematics. August 2024. Potsdam, Germany.

“Cairn.jl: Enhanced Molecular Dynamics for Active Learning.”
JuliaCon. July 2024. Eindhoven, Netherlands.

“Active learning of energy-based models by stochastic Stein variational gradient descent.”
SIAM Conference on Uncertainty Quantification (SIAM UQ). March 2024. Trieste, Italy.

“Adaptive importance sampling for gradient-based dimension reduction in stochastic systems.”
International Conference on Uncertainty Quantification in Computational Science and Engineering (UNCECOMP). June 2023. Athens, Greece.

“Gaussian process latent force models for virtual sensing of offshore wind turbines.”
European Workshop on Structural Health Monitoring (EWSHM). July 2022. Palermo, Italy.

Poster Presentations

“Goal-oriented learning and uncertainty quantification of stochastic differential equations.”
MIT Center for the Exascale Simulation of Coupled High Enthalpy Fluid-Structure Interactions (CHEFSI). April 2026. Cambridge, MA.

“A goal-oriented loss for learning transition times with machine learning potentials.”
ICMS Workshop on Computational Materials Science and Mathematics at the Particle and Atomistic Scales (CoMPASs). November 2025. Edinburgh, UK.

“Data curation for machine learning interatomic potentials by determinantal point processes.”
ICLR Workshop on AI for Accelerated Materials Design. April 2025. Singapore.

“Using error bounds on molecular properties for goal-oriented learning of machine learning potentials.”
MIT Center for the Exascale Simulation of Material Interfaces in Extreme Environments (CESMIX). April 2025. Cambridge, MA.

“Active subspaces for Bayesian inference of machine learning interatomic potential models.”
MIT Center for the Exascale Simulation of Material Interfaces in Extreme Environments (CESMIX). Oct. 2023. Cambridge, MA.

“Bayesian modeling and active learning for molecular dynamics: fitting machine learning interatomic potentials to data.”
CECAM Workshop on Error Control in First-Principles Modelling. June 2022. Lausanne, Switzerland.