Updates
Below is a selected recent archive of talks, papers, awards, group milestones, and other activity across the research program.
2026
- September 2 Liliang has successfully defended her PhD Dissertation, titled ``General Theory and Variational Methods for Sequential Bayesian Learning." Congratulations Liliang!
- September The group welcomes Eden Powers and Nicholas Lototsky as PhD students, and Zheng Guo as a Postdoctoral fellow. Eden comes to us after obtaining a Bachelors in Mathematics at Longwood University and Nicholas comes to us after obtaining a Bachelors in Aerospace Engineering from the University of Southern California. Zheng is a Schmidt AI for science postdoctoral fellow.
- August 20 Alex gave a talk titled "A probabilistic perspective on data assimilation: system identification, sequential learning, and approximation error" at the AFRL Data Assimiliation for Shock-Driven Flows Meeting. Slides are available here.
- June 9-10 Alex gave a talk on block-local tensor decomposition for adaptive mesh refinement in thermal radiation transport at the SPARC Annual Colloquium, Los Alamos, NM. The preprint is available here.
- June 4 Thomas Dixon successfully defended his thesis on theoretical extensions and automation of multi-fidelity statistical estimation and its application to stochastic optimization.
- June 2-3 Alex gave a talk on multi-fidelity inverse problems at the LANL Data Science at Scale Seminar Series. Slides are available here.
- April 29-30 Alex presented at the AFOSR MURI workshop on tensor networks for high-dimensional approximation, algorithms, analysis, and applications.
- April 14-15 Alex presented at the MICDE Predictive Science Symposium on multi-fidelity methods and joined a panel on uncertainty quantification. Sanjan won a best poster prize for work on multi-fidelity inverse problems.
- March 23-26 Alex presented at IPAM Workshop I: Multi-Fidelity Methods for Fusion Plasma Physics. Slides are available here.
- March 22-25 The group contributed multiple talks at SIAM UQ26 on inverse problems, variational inference, generative models, transport maps, and multi-fidelity estimation.
- January 12-16 The group had three papers at AIAA Scitech related to multi-fidelity inference and Hall thruster modeling. They are available here, here, and here.
2025
- October 27-31 Alex gave a talk at the IMSI workshop Optimal Control and Decision Making Under Uncertainty for Digital Twins in Chicago, IL. Slides are available here.
- October 21 The paper "Uncertainty quantification of a multi-component Hall thruster model at varying facility pressures" was published in the Journal of Applied Physics as a featured article. It is available here.
- September 10 Alex gave a talk on multi-fidelity sampling methods at the SPARC Colloquium, Los Alamos, NM. Slides are available here.
- September 1 Alex started his sabbatical at Sandia National Laboratories.
- August 11-15 Alex gave a talk on errors in data assimilation at the workshop Mathematical and Computational Foundations of Digital Twins at CIRM in Marseille, France. Slides are available here.
- July Doruk defended his thesis, Incremental Tensor Decompositions for Scientific Machine Learning and Bayesian Inference.
- July 20-24 The group presented multiple papers at the 18th U.S. National Congress on Computational Mechanics. Sanjan won the UQ-TTA student paper competition in uncertainty quantification.
- July 14 Our paper with LANL collaborators on thermal radiation transport with tensor trains was published in the Astrophysical Journal. It is available here.
- May 9 Thomas Marks's paper on GPU-accelerated kinetic Hall thruster simulations in WarpX was published in the Journal of Electric Propulsion. It is available here.
- March 3-7 The group presented at SIAM CSE25 on tensor decompositions, Hall thruster modeling, online inference, multi-fidelity estimation, and model error.
2024
- October Nick's paper on Bayesian identification of nonseparable Hamiltonians with multiplicative noise was published in Computer Methods in Applied Mechanics and Engineering.
- September Josh's paper on Hall thruster model improvement by multidisciplinary uncertainty quantification was published in the Journal of Electric Propulsion.
- September Thomas Dixon's paper on covariance expressions for multi-fidelity sampling with multi-output, multi-statistic estimators was published in SIAM Journal on Uncertainty Quantification.
- July 21-26 The group had several presentations at the World Congress on Computational Mechanics spanning digital twins, stochastic optimization, Bayesian system identification, and multi-fidelity sampling.
- June 23-28 The group had three papers at IEPC in Toulouse on Hall thruster simulations, particle-in-cell acceleration, and tensor-network compression for electric propulsion.
- June 3-7 Thomas Dixon presented multi-fidelity optimization under uncertainty with robust constraints at ECCOMAS 2024.
- June Nick's paper on likelihood-based generalization of Markov parameter estimation and multiple shooting objectives in system identification was published in Physica D.
- May 28-31 Doruk gave an invited talk on incremental tensor decompositions for compressing image-based data streams at SIAM Imaging Science 2024.
- March 10 Brian and Doruk's paper on low-rank tensor-network encodings for video-to-action behavioral cloning was published in Transactions on Machine Learning Research.
- January 8-12 Thomas Marks and Josh Eckels had papers at AIAA Scitech 2024 on optimization under uncertainty, optimal experimental design, and surrogate modeling for propulsion systems.
2023
- December The group welcomed Kamal Abdulraheem as a MIDAS Eric and Wendy Schmidt AI in Science Fellow.
- November The group welcomed Sanjan Muchandimath as a Ph.D. student. Sanjan was previously a master's student at U-M.
- November Liliang and Doruk presented at the 2023 Michigan Data Science and AI Summit. Liliang won a best oral communication award for the poster titled "FBOVI: An Efficient Scalable and Flexible Variational Approach for Online State-Parameter Estimation of Partially Observable Systems."
- October The group welcomed Thomas Marks as a postdoctoral fellow, working on large-scale plasma simulations and the Joint Advanced Propulsion Institute (JANUS).
- October 22-25 Alex gave a talk at the Advances in Computational Mechanics (ACM 2023), a conference celebrating the 80th birthday of Thomas J. R. Hughes in Austin, Texas. His talk was titled "Bayesian learning of dynamical systems, the role of stochastic models for ensuring robustness to noise and sparse data."
- October 8-11 Alex gave a talk at the 2023 SES Annual Technical Meeting in Minneapolis, Minnesota. His talk was titled "Algorithms and Approaches for Multifidelity Uncertainty Quantification." It was a keynote in a minisymposium.
- October 1 Our paper on "Multifidelity uncertainty quantification with models based on dissimilar parameters," with USC and Sandia National Laboratories, was published in Computer Methods in Applied Mechanics and Engineering. It is available here.
- September Doruk became a MICDE Graduate Fellow.
- September The group welcomed Artem Mustaev as a Ph.D. student from the University of Illinois.
- September 24-27 Alex and Thomas gave talks at the 2nd IACM Conference on Mechanistic Machine Learning and Digital Engineering for Computational Science, Engineering and Technology (MMLDE/CSE 2023) in El Paso, Texas. Thomas presented "Multi-output estimation for enhanced variance reduction applied to stochastic optimization" and Alex presented "Parameter-state estimation in the presence of sensor-model manipulation."
- September 15 Alex gave a talk in the University of Michigan Controls Seminar titled "Bayesian learning of dynamical systems under uncertainty."
- July 23-27 Doruk, Liliang, and Thomas presented their work at the 17th U.S. National Congress on Computational Mechanics in Albuquerque, New Mexico. Doruk presented "Solving Inverse Problems in High-Dimensional Data: An Approach for Optimal Sensor Placement with Incremental Tensor-Train Decomposition." Liliang presented "A Novel Online Variational Inference Algorithm for State-Parameter Estimation of Hidden Linear Models." Thomas presented work on multi-output approximate control variates.
- May Nick defended his Ph.D. thesis, Generalization of System Identification Objective Functions Through Stochastic Hidden Markov Models for Regularization, Smoothness, and Uncertainty Quantification.
- May Alex won an NSF CAREER Award: "CAREER: New Foundations for Multi-Fidelity Prediction, Estimation, and Learning Under Uncertainty in Dynamical Systems."
- May 24-26 Alex gave a talk on "Algorithms and approaches for multifidelity uncertainty quantification" at the ASA/IMS Spring Research Conference 2023 at Banff Centre, Alberta, Canada.
- April Josh won a NASA Space Technology Graduate Research Opportunities (NSTGRO) fellowship.
- April 6-7 Alex gave an invited talk on "Methods and approaches to benchmark data-driven modeling in sparse and noisy data-regimes" at the USACM Workshop on Establishing Benchmarks for Data Driven Modeling of Physical Systems at the University of Southern California.
- March Alex gave an invited talk on "Opportunities and challenges for uncertainty quantification in the analysis, design, and control of complex engineering systems" at NASA Langley Research Center for the Uncertainty Quantification Seminar Series.
- March 24 Doruk won second prize at the Michigan Institute for Computational Discovery & Engineering (MICDE) Annual Symposium.
- February 26-March 3 Doruk, Thomas, and Alex presented their work at SIAM CSE in Amsterdam. Doruk presented the poster "An incremental tensor-train decomposition for high-dimensional data streams," with the corresponding preprint available here. Thomas presented work on multi-output approximate control variates. Alex presented "Graph Construction in Multi-Fidelity Networked Surrogates."
- January 23-27 Carleen and Josh presented their papers at AIAA Scitech. Carleen's paper was on online parameter estimation with trajectory optimization for dynamic soaring. Josh's paper, a collaboration with PEPL, was on optimal experimental design to learn reduced-fidelity models for porous electrosprays. Alex also contributed to two additional collaborations with Sandia National Laboratories and NASA on multifidelity uncertainty quantification, available here and here.
2022
- December 6-9 Nick's paper Bayesian Identification of Nonseparable Hamiltonian Systems Using Stochastic Dynamic Models appeared in the proceedings of the Conference on Decision and Control (CDC22), held in Cancun, Mexico. This was joint work with Harsh Sharma and Boris Kramer at UC San Diego.
- November The group received a DURIP award for "Graphics Processing Units based Computing System for Emerging Hypersonics Solvers." The PI for this project is Professor Venkat Raman and the other co-PI is Assistant Professor Aaron Towne. The project funds a new computer system for advanced simulation and analysis algorithms tailored to GPU-based computing.
- November 17 Alex gave a talk at the Johns Hopkins University Civil and Systems Engineering Department graduate seminar titled "Multi-fidelity approaches to uncertainty quantification: sampling and surrogates."
- October 16-19 Alex presented at INFORMS 2022 in Indianapolis, Indiana in the Science-integrated Statistical Learning session. His talk was titled "Compositional Multifidelity Models for Uncertainty Quantification via Directed Graphs." Slides are available here.
- September 26-30 Nick and Doruk presented their recent research at the SIAM Conference on Mathematics of Data Science (MDS22) in San Diego, California. Nick's talk was "Enforcing Physical Structure in Bayesian Learning of Dynamical Systems: Stability and Energy Conservation," and Doruk's was "Incremental Tensor Train Decomposition for Compression and Approximation of High-Dimensional Streaming Datasets."
- August 18-19 Alex gave an invited talk on "Uncertainty Quantification with Multi-Fidelity Networks" at the USACM Thematic Conference on Uncertainty Quantification for Machine Learning Integrated Physics Modeling in Crystal City, Arlington, Virginia.
- June Josh presented his paper at the International Electric Propulsion Conference in Boston, Massachusetts. The paper, Simulation-based surrogate methodology of electric field for electrospray emitter geometry design and uncertainty quantification, developed a neural-network surrogate for predicting electric field strength in electrospray emitters and studied sensitivity to emitter geometry.
- June Nick and Alex presented recent research at the 8th European Congress on Computational Methods in Applied Sciences and Engineering (ECCOMAS Congress 2022) in Oslo, Norway. Nick's talk was "Accounting for Model Uncertainty in the Identification of Partially Known Models." Alex's talk was "Estimating Approximate Control Variate Weights: with Applications in Importance Sampling and Rare Event Simulation." Slides are available here.
- May 2-6 Alex presented at the Workshop on Multilevel and multifidelity sampling methods in UQ for PDEs at the Erwin Schrodinger Institute. The talk was "MFNETS: Multifidelity surrogate modeling of ensembles of information sources through directed acyclic graphs." Slides are available here.
- April Nick, Doruk, Trung, and Alex presented their research at SIAM UQ22 on topics ranging from Bayesian inference for dynamical systems, to deep learning for inverse design in dynamical systems, to a new multi-fidelity surrogate approach for ensembles of information sources. Alex's slides are available here.
- March Our paper on experimental design for multi-fidelity surrogate construction of multi-disciplinary systems was published in the International Journal of Numerical Methods in Engineering.
- January Hang's paper on a novel estimator for uncertainty quantification in dynamical systems was published in the Journal of Computational and Nonlinear Dynamics.
- January Doruk's paper on a deep-learning approach to inverse design of self-oscillating sheets was published in Neural Computing and Applications. This was joint work with Silas Alben and Robert Deegan at U-M.
- January Our paper with Micheline Soley, Paul Bergold, and Victor Batista on functional tensor-train methods for quantum dynamics simulations was published in the Journal of Chemical Theory and Computation.
- January Koray's paper on dynamic multi-agent assignment was published in the IEEE Transactions on Control of Networked Systems.
- January 3-7 We had two papers at AIAA Scitech: one on Bayesian inference for electrospray thrusters with the Plasmadynamics and Electric Propulsion Laboratory, available here, and one with NASA and Sandia National Laboratories on multifidelity uncertainty quantification for trajectory planning, available here.
2021
- December Hang Yang successfully defended his Ph.D.
- September The group welcomed two new graduate students, Thomas Dixon and Joshua Eckels.
- August Brian and Nick received MICDE fellowships for research in scientific computing and computational discovery. The press releases are here and here.
- August 17-20 Hang achieved third place in the student paper competition at the 17th International Conference on Multibody Systems, Nonlinear Dynamics, and Control. His paper, Multifidelity Uncertainty Quantification for Online Simulations of Automotive Propulsion Systems, showed how intrusive polynomial chaos and approximate control variates can be combined to reduce both bias and variance in dynamical-system UQ.
- August 9-11 Alex presented work with Audelia Szulman, Collin Whittaker, and Ben Jorns from PEPL at the AIAA Propulsion and Energy Forum. The paper, Robust Design of Electrospray Emitters, described a method for generating robust feasible electrospray designs.
- June 28-July 1 Brian presented our paper, Behavioral Cloning in Atari Games Using a Combined Variational Autoencoder and Predictor Model, at the IEEE Congress on Evolutionary Computation.
- June 28-30 Trung presented our work on approximate control variates robust to misspecified covariance matrices at the 4th International Conference on Uncertainty Quantification in Computational Sciences and Engineering. The paper is available here.
- June 6-7 Nick presented a poster at the 3rd Annual Learning for Dynamics and Control Conference, hosted by ETH Zurich, on a robust objective for identifying linear systems from input-output data. The paper is available here.
- May 25-28 Alex presented at the Engineering Mechanics Institute / Probabilistic Mechanics and Reliability 2021 Conference on Bayesian system identification. Slides are available here.
- May 7 Alex presented at the UC San Diego Mechanical and Aerospace Engineering Dynamics and Control seminar. Slides are available here.
- April 5 Hang received the Distinguished Leadership Award from the College of Engineering.
- March 1-5 Trung and Nick presented recent research at SIAM CSE21.
- March 3 We released a preprint on inverse design of a self-oscillating gel using deep learning. The preprint, supplementary materials, and code are available here, here, and here.
- February 25 We released a preprint on reverse-mode differentiation for tensor networks with arbitrary network topologies. The paper is available here.
- February 1 We released a preprint on ensemble approximate control variate estimators. The paper is available here.
2020
- December 14-15 Alex presented at the Machine Learning in Science & Engineering Conference hosted by the Columbia Data Science Institute on Bayesian nonlinear system identification. The presentation is available here.
- December 14-18 Nick presented our paper Bayesian Identification of Hamiltonian Dynamics from Symplectic Data at CDC 2020.
- September 1 Nick's paper Bayesian system ID: optimal management of parameter, model, and measurement uncertainty was accepted to Nonlinear Dynamics.
- September 1 Our collaborator John Jakeman created tutorials on the recently published MFNETS sampling framework for multifidelity UQ as part of PyApprox. One tutorial is available here.
- July 1-3 Hang presented at the 2020 American Control Conference on our paper Uncertainty Quantification Using Generalized Polynomial Chaos for Online Simulations of Automotive Propulsion Systems.
- May 4-5 Alex presented at the Workshop on Multilevel and multifidelity sampling methods in UQ for PDEs at the Erwin Schrodinger Institute. The talk was "Sampling algorithms for generalized model ensembles in multifidelity uncertainty quantification." Slides are available here.
- January 12-16 Alex gave a talk at the Physics Informed Machine Learning Workshop hosted by the Center for Nonlinear Studies at LANL in Santa Fe, New Mexico: "Bayesian approaches for data-driven learning of dynamical systems." Slides are available here.
2019
- October 15 Alex gave a talk at the Department of Mathematics at the University of Maryland, College Park: "Compression algorithms for enabling high-dimensional motion planning." Slides are available here.
- August 14-16 Alex gave a tutorial at the 2019 UQ Summer School at USC in Los Angeles: "Tensor decompositions and their UQ applications." Slides are available here.
- July 28-August 1 Alex gave a talk at the 15th U.S. National Congress on Computational Mechanics in Austin, Texas: "Unifying multifidelity sampling approaches as approximate control variates."
- June 24-26 Alex gave a talk at the 3rd International Conference on Uncertainty Quantification in Computational Sciences and Engineering in Crete, Greece: "New approaches to learn low-rank models of dynamical systems from streaming data."
- June 20 Alex gave an invited talk at LIMSI-CNRS in Orsay, France: "Compression algorithms for enabling high-dimensional motion planning."
- June 6-7 Alex gave a talk at the Physics Informed Machine Learning Workshop at the University of Washington in Seattle: "Scalable learning of dynamical systems." Slides are available here.
- May 23 Alex gave an invited talk at Sandia National Laboratories in Albuquerque: "Compression algorithms for enabling high-dimensional motion planning."
2018
- July 22-27 Alex gave a talk at the 13th World Congress in Computational Mechanics in New York: "Multifidelity model management using latent variable networks."
- June 27-29 Ezra Tal (MIT) gave a talk about our paper at ACC in Milwaukee: "Continuous tensor train-based dynamic programming for high-dimensional zero-sum differential games."
- June 11-15 Alex gave a talk at the 6th European Conference on Computational Mechanics in Glasgow, Scotland.
- June 4-6 Alex gave a talk at the USC Workshop on Research Challenges and Opportunities at the Interface of Machine Learning and Uncertainty Quantification in Los Angeles: "Regression in low-rank functional formats."
- April 16-19 Alex gave a talk at the SIAM Conference on Uncertainty Quantification in Orange County, California: "Sparse regularization for low-rank regression."
- January 30-February 1 Alex participated in the DOE Workshop on Scientific Machine Learning in Rockville, Maryland.
- January 22 Alex gave a talk at the Physics Constrained Machine Learning Workshop, hosted by the Center for Nonlinear Studies at LANL in Santa Fe: "Multifidelity model management using latent variable Bayesian networks."
- January 19 Alex gave a talk at the U-M Aerospace graduate seminar: "Compression algorithms for enabling high-dimensional motion planning."
- January 18 Alex gave a talk at the U-M Aerospace graduate seminar: "Compression algorithms for enabling high-dimensional motion planning."
- January 1 Alex started at the University of Michigan.