"Low-Rank Adaptation (LoRA) and Parameter-Efficient Fine-Tuning" - FSU Department of Scientific Computing Machine Learning Seminar - April 10, 2026
"Recent progress on sparse approximation techniques for parametric PDEs" - One World Mathematics of INformation, Data, and Signals (1W-MINDS) Seminar, online - January 15, 2026.
"Data-Efficient Operator Learning for PDEs: Sparse Recovery and Deep Learning" - Department of Mathematics Colloquium, Iowa State University, Ames, IA - November 2025.
"Optimization challenges in compressed sensing and machine learning with generative models" - FSU Department of Scientific Computing Machine Learning Seminar - November 2025.
"Data-Efficient Operator Learning for PDEs: Sparse Recovery and Deep Neural Networks" - Department of Scientific Computing Colloquium, Florida State University - September 2025.
"Sample-efficient surrogate modeling for computational mechanics via active learning and sparse approximation" - 18th U.S. National Congress on Computational Mechanics (USNCCM18), Chicago, IL - July 23, 2025.
"Optimal deep learning of holomorphic operators between Banach spaces" - International Conference on Spectral and High-Order Methods (ICOSAHOM), McGill University, Montreal, QC, Canada - July 16, 2025.
"Sample-Efficient Active Learning Strategies with Generalized Christoffel Functions for Nonlinear PDEs" - International Conference on Spectral and High-Order Methods (ICOSAHOM), McGill University, Montreal, QC, Canada - July 15, 2025.
"Sample-Efficient Active Learning Strategies for Scientific Computing" - CRM Workshop on Approximation and Learning in High Dimensions, Centre de Recherches Mathématiques, Université de Montréal, Montreal, QC, Canada - June 11, 2025.
"Sample-Efficient Active Learning Strategies for Deep Learning in Scientific Computing" - SIAM Conference on Computational Science and Engineering (CSE25), Fort Worth, TX - March 4, 2025.
"Sample-Efficient Active Learning Strategies for Deep Learning in Scientific Computing" - ACM Seminar, Department of Mathematics, Florida State University - February 11, 2025.
"Sample-Efficient Active Learning Strategies for Deep Learning in Scientific Computing" - SIAM Conference on Mathematics of Data Science, Atlanta, GA - October 25, 2024.
"Christoffel Sampling for Machine Learning (CS4ML): A general framework for active learning with arbitrary data based on Christoffel functions" - Poster, SIAM Conference on Mathematics of Data Science, Atlanta, GA - October 23, 2024.
"A unified framework for learning with nonlinear model classes from arbitrary linear samples" - Poster, International Conference on Machine Learning (ICML), Vienna, Austria - July 24, 2024.
"Sample-Efficient Active Learning Strategies for Deep Learning in Scientific Computing" - Summer Meeting, Canadian Mathematical Society, Saskatoon, SK, Canada - June 1, 2024.
"Active Learning for Scientific Computing" - FSU Department of Scientific Computing Machine Learning Seminar - March 29, 2024.
"Sample-Efficient Techniques for Deep Learning of High-Dimensional Banach-Valued Functions" - SIAM Conference on Uncertainty Quantification (UQ24), Trieste, Italy - February 29, 2024.
"Learning High-Dimensional Banach-Valued Functions from Limited Data with Deep Neural Networks" - Machine Learning Seminar, Department of Mathematics, Florida State University - January 26, 2024.
"Neural Operators" - ACM Seminar, Department of Mathematics, Simon Fraser University - December 15, 2023.
"Learning High-Dimensional Banach-Valued Functions from Limited Data with Deep Neural Networks" - Southeastern-Atlantic Regional Conference on Differential Equations (SEARCDE) - November 18, 2023.
"Compressed sensing, neural networks, and active learning for computational science" - FSU ISC 5934r, Introductory Seminar on Research in Computational Science - November 17, 2023.
"Neural Operators" - FSU Department of Scientific Computing Machine Learning Seminar - October 13, 2023.
"Learning High-Dimensional Banach-Valued Functions from Limited Data with Deep Neural Networks" - DMS Applied and Computational Mathematics Seminar, Auburn University, Auburn, AL - October 6, 2023.
"Efficient, Reliable, and Interpretable Deep Learning for Science and Engineering" - FSU First Year Assistant Professor Program Poster Session - September 9, 2023.
"Learning High-Dimensional Banach-Valued Functions from Limited Data with Deep Neural Networks" - International Congress on Industrial and Applied Mathematics (ICIAM), Waseda University, Tokyo, Japan - August 24, 2023.
"CAS4DL: Christoffel Adaptive Sampling for Deep Learning in Scientific Computing Applications" - FSU Department of Scientific Computing Machine Learning Seminar - April 7, 2023.
"Effective deep neural network architectures for learning high-dimensional Banach-valued functions from limited data" - Los Alamos National Laboratory SciML Seminar, online - March 14, 2023.
"Effective Deep Neural Network Architectures for Learning High-Dimensional Banach-Valued Functions from Limited Data" - SIAM Conference on Computational Science and Engineering (CSE23), Amsterdam, Netherlands - February 28, 2023.
"Effective deep neural network architectures for learning high-dimensional Banach-valued functions from limited data" - Applied and Computational Mathematics Seminar, Georgia Tech, Atlanta, GA - February 10, 2023.
"Effective deep neural network architectures for learning high-dimensional Banach-valued functions from limited data" - FSU Mathematics Data Science and Machine Learning Seminar - February 3, 2023.
"Effective deep neural network architectures for learning high-dimensional Banach-valued functions from limited data" - FSU ACM Seminar - October 25, 2022.
"Effective deep neural network architectures for learning high-dimensional Banach-valued functions from limited data" - AMS Fall Southeast Sectional Meeting, University of Tennessee Chattanooga - October 15, 2022.
"Learning Near-Best Polynomial and Neural Network Approximations to High-Dimensional, Banach-valued Functions from Scarce Data" - SIAM Conference on the Mathematics of Data Science - September 27, 2022.
"Effective deep neural network architectures for learning high-dimensional Banach-valued functions from limited data" - International Conference on Computational Harmonic Analysis, KU Eichstätt, Eichstätt, Germany - September 15, 2022.
"Efficient algorithms for computing near-best polynomial approximations to high-dimensional, Hilbert-valued functions from limited samples" - CAIMS West Coast Optimization Meeting, UBC Okanagan, BC, Canada - June 13, 2022.
"Efficient sparse recovery and neural network approximation for high-dimensional scientific ML" - AARMS CRG Workshop on Mathematical Foundations of Scientific ML, Memorial University of Newfoundland, Canada - June 1, 2022.
"Efficient algorithms for high-dimensional uncertainty quantification" - Computational UQ: Mathematical Foundations, Methodology & Data, Erwin Schrödinger International Institute for Mathematics and Physics, Vienna, Austria - May 10, 2022.
"Improving efficiency of deep learning approaches for scientific machine learning" - SIAM Conference on Uncertainty Quantification (UQ22), Atlanta, GA - April 15, 2022.
"Scientific machine learning, compressed sensing, and the future of data science" - Department of Scientific Computing Colloquium, Florida State University - November 17, 2021.
"The rate-distortion explanation identifies causal mutations driving drug resistance in bacterial whole-genome sequence data" - Machine Learning in Computational Biology, online - November 23, 2021.
"Deep Neural Network Approximation of High-Dimensional Hilbert-Valued Functions From Limited Data" - SIAM Southeastern Atlantic Section Annual Meeting, online - September 19, 2021.
"Deep Neural Network Approximation of High-Dimensional Hilbert-Valued Functions From Limited Data" - International Conference on Computational Harmonic Analysis, online - September 17, 2021.
"Learning High-Dimensional Hilbert-Valued Functions With Deep Neural Networks From Limited Data" - AAAI 2021 Spring Symposium on Combining Artificial Intelligence and Machine Learning with Physical Sciences, online - March 22, 2021.
"Sparse Reconstruction Techniques for Approximation of Solutions to High-Dimensional Parameterized PDEs" - SIAM Conference on Computational Science and Engineering (CSE21), online - March 3, 2021.
"The gap between theory and practice in function approximation with deep neural networks" - CRM Applied Mathematics Seminar, McGill University - February 17, 2020.
"Practical approximation in high dimension with ReLU deep neural networks" - Scientific Computing, Applied and Industrial Mathematics Seminar, University of British Columbia - November 19, 2019.
"On the gap between theory and practice in deep learning" - Math Department Colloquium, Western Washington University - November 7, 2019.
"On the gap between theory and practice in deep learning" - Operations Research Seminar, Simon Fraser University - October 3, 2019.
"Practical approximation in high dimension with ReLU deep neural networks" - Laboratory Jacques-Louis Lions, Sorbonne University, Paris, France - July 3, 2019.
"A mixed l1-regularization approach for sparse simultaneous approximation of parameterized PDEs" - Laboratory Jacques-Louis Lions, Sorbonne University, Paris, France - July 2, 2019.
"High-dimensional function approximation with ReLU deep neural networks" - Canadian Applied and Industrial Mathematics Society Annual Meeting, Whistler, BC, Canada - June 10, 2019.
"High-dimensional function approximation with ReLU deep neural networks" - 16th International Conference on Approximation Theory, Vanderbilt University, Nashville, TN - May 19, 2019.
"Energy norm regularized sparse simultaneous reconstruction of solutions to parameterized PDEs" - SIAM Conference on Computational Science and Engineering, Spokane, WA - February 25, 2019.
"Joint-sparse recovery for high-dimensional parametric PDEs" - Workshop on Numerical Analysis and Approximation Theory Meets Data Science, Banff International Research Station, Banff, Alberta, Canada - April 23, 2018.
"Joint-sparse recovery for high-dimensional parametric PDEs" - Workshop on UQ for Inverse Problems in Complex Systems, Isaac Newton Institute, Cambridge University, UK - April 12, 2018.
"Joint-sparse recovery for high-dimensional parametric PDEs" - Computational and Applied Mathematics Seminar, Georgia Tech, Atlanta, GA - March 5, 2018.
"Sparse recovery of Hilbert-valued signals with applications to high-dimensional parametric PDEs" - QUIET 2017, SISSA, Trieste, Italy - July 20, 2017.
"Sparse recovery of Hilbert-valued signals with applications to high-dimensional parametric PDEs" - SIAM Annual Meeting, Pittsburgh, PA - July 14, 2017.
"Sparse recovery of Hilbert-valued signals with applications to high-dimensional parametric PDEs" - Computational and Applied Mathematics Seminar, Oak Ridge National Laboratory, Oak Ridge, TN - May 22, 2017.
"Global reconstruction of solutions to parametric PDEs via compressed sensing" - SIAM Conference on Computational Science and Engineering, Atlanta, GA - February 27, 2017.
"Global reconstruction of solutions to parametric PDEs via compressed sensing" - Dagstuhl Seminar on Uncertainty Quantification and High Performance Computing, Schloss Dagstuhl, Wadern, Germany - September 13, 2016.
"Explicit cost bounds of stochastic Galerkin approximations for parameterized PDEs with random coefficients" - SIAM Conference on Uncertainty Quantification, Lausanne, Switzerland - April 5, 2016.
"Learning High-Dimensional Functions: Approximation, Sampling, and Algorithms" - Minisymposium organizer, SIAM Conference on Uncertainty Quantification (UQ24), Trieste, Italy - February 27-March 1, 2024.
"Black box methods for efficient learning in high-dimensional scientific computing" - Minisymposium organizer, 10th International Congress on Industrial and Applied Mathematics (ICIAM), Waseda University, Tokyo, Japan - August 20-25, 2023.
"Learning Deep Neural Networks and Sparse Approximations from Limited Data for High-Dimensional Problems in Computational Science and Engineering" - Minisymposium organizer, SIAM Conference on Computational Science and Engineering (CSE23), Amsterdam, Netherlands - February 26-March 3, 2023.
"Deep Learning and Sparse Approximation for High-Dimensional Problems in Data Science" - Minisymposium organizer, SIAM Conference on Mathematics of Data Science, San Diego, CA - September 26-30, 2022.
"Safety and security in artificial intelligence and deep learning" - Minisymposium organizer, SIAM Conference on Mathematics of Data Science, Cincinnati, OH - May 5-7, 2020.
"Deep learning and sparse approximation for high-dimensional problems in uncertainty quantification" - Minisymposium organizer, SIAM Conference on Uncertainty Quantification, TU Munich - March 24-27, 2020. Conference cancelled due to COVID-19.
Foundations of Computational Mathematics (FoCM20) - Organizing committee member, Vancouver, BC, Canada - June 15-24, 2020. Conference cancelled due to COVID-19.
SFU Postdoctoral Research Day - Organizer, Simon Fraser University, Vancouver, BC, Canada - March 31, 2020.
Joint UBC and SFU Career Night - Organizer, Simon Fraser University, Vancouver, BC, Canada - March 10, 2020.
PIMS CRG Summer School: Deep Learning for Computational Mathematics - Organizer, Simon Fraser University, Burnaby, BC, Canada - July 22-25, 2019.
Ask A Scientist - Community outreach event organized by the FSU Department of Physics - February 6, 2025 and November 1, 2024.
"Christoffel Sampling for Machine Learning (CS4ML): A general framework for active learning with arbitrary data based on Christoffel functions" - SIAM Conference on Mathematics of Data Science, Atlanta, GA - October 23, 2024.
"A unified framework for learning with nonlinear model classes from arbitrary linear samples" - International Conference on Machine Learning (ICML), Vienna, Austria - July 24, 2024.
"Efficient, Reliable, and Interpretable Deep Learning for Science and Engineering" - FSU First Year Assistant Professor Program Poster Session - September 9, 2023.
"Stability-performance barriers and practical function approximation with deep neural networks" - DeepMath Conference, online - November 5, 2020.
"Learning high-dimensional Hilbert-valued functions with deep neural networks from limited data" - DeepMath Conference, online - November 5, 2020.
"On the gap between theory and practice in deep learning" - DeepMath Conference, Princeton Club, New York, NY - October 31, 2019.
"Reconstructing high-dimensional Hilbert-valued functions via compressed sensing" - 13th International Conference on Sampling Theory and Applications, Université de Bordeaux, Bordeaux, France - July 9, 2019.
This page lists recent and selected talks, posters, workshops, and organized events. A more complete list of presentations and professional activities is available in my CV.
The cover photo was taken at the Golden Gate Bridge Welcome Center in San Francisco, CA.