Talks
- June 2024: Geometry and Convergence of Natural Policy Gradient Methods, Seminar on Learning Theory and Statistical Optimization, University of Oxford
- June 2024: Geometry of Optimization in Scientific Machine Learning and Reinforcement Learning, Invited talk, Geometric Deep Learning workshop, University of Cambridge
- January 2024: Natural Gradients for Scientific Machine Learning, Post Graduate Seminar, Chair of Mathematics of Information Processing, RWTH Aachen
- April 2023: Theoretical Analysis of Boundary Penalties for NN-based PDE Solvers, Machine Learning + X Seminars 2023, Brown University, Providence, online
- February 2023: Geometry of Sequential Decision Problems, Optimization and Data Science Seminar, University of California, San Diego, online
- November 2022: Geometry of Markov decision processes, Annual meeting of the Priority Programme Theoretical Foundations of Deep Learning (SPP 2298), Evangelische Akademie Tutzing, Germany
- October 2022: Geometry of Natural Policy Gradient Methods, Applied Math Colloquium, University of California, Los Angeles, USA
- September 2022: Minisyposium Algebraic Geometry and Machine Learning at the SIAM Conference on Mathematics of Data Science (MDS22), Town and Country Resort, San Diego, California, USA
- August 2022: Workshop on Algebraic Geometry, Combinatorics, and Machine Learning, Max Planck Institute for Mathematics in the Sciences, Leipzig, Germany
- May 2022: Algebraic Statistics 2022, University of Hawai’i at Manoa, Honolulu, HI, USA
- April 2020: Math Machine Learning seminar MPI MIS + UCLA
Poster presentations
January 2024: Fisher-Rao Gradient Flows of Linear Programs and State-Action Natural Policy Gradients, Symposium on Sparsity and Singular Structures 2024, RWTH Aachen University
February 2024: Geometry and Convergence of Natural Policy Gradient Methods, Symposium on Sparsity and Singular Structures 2024, RWTH Aachen University
January 2024: Geometry and Convergence of Natural Policy Gradient Methods, Mini-Workshop on Reinforcement Learning, University of Mannheim
June 2022: Solving infinite-horizon POMDPs with memoryless stochastic policies in state-action space, Multidisciplinary Conference on Reinforcement Learning and Decision Making, Brown University
April 2022: The Geometry of Memoryless Stochastic Policy Optimization in Infinite Horizon Partially Observable Markov Decision Processes, International Conference of Learning Representations, online
November 2021: A Posteriori Estimates and Convergence Guarantees for Neural Network Based PDE solvers, Deep learning and partial differential equations at the Sir Isaac Newton Institute, Cambridge, UK
October 2021: The Geometry of Memoryless Stochastic Policy Optimization in Infinite-Horizon Partially Observable Markov Decision Processes, Geometry & Learning from Data, BIRS workshop hosted by Casa Matem ́atica Oaxaca (CMO), held online, poster available
August 2021: The geometry of discounted stationary distributions of Markov decision processes, Workshop on Workshop on Mathematics of deep learning at the Sir Isaac Newton Institute, Cambridge, UK, poster available
August 2021: The geometry of discounted stationary distributions of Markov decision processes, Conference on Mathematics of Machine Learning at the Zentrum für interdisziplinäre Forschung, Bielefeld, Germany, poster available
April 2020: Deep Ritz revisited, ICLR workshop on Integration of Deep Neural Models and Differential Equations, held virtually, fulltext available
April 2020: On the space-time expressivity of residual networks, ICLR workshop on Integration of Deep Neural Models and Differential Equations, held virtually, fulltext available | ICLR workshop DeepDiffEq