6 papers
Data-Adaptive Learning of Dynamical Systems by Matching Transfer Operators and Invariant Measures
Yinong Huang, Jonah Botvinick-Greenhouse, Yunan Yang
Trajectory-based learning of dynamical systems is often fragile in the presence of noise, chaos, or sparse observations, as small pointwise errors can rapidly amplify. We introduce…
On the Unique Recovery of Transport Maps and Vector Fields from Finite Measure-Valued Data
Jonah Botvinick-Greenhouse, Yunan Yang
We establish guarantees for the unique recovery of vector fields and transport maps from finite measure-valued data, yielding new insights into generative models, data-driven dynam…
Measure-Theoretic Time-Delay Embedding
Jonah Botvinick-Greenhouse, Maria Oprea, Romit Maulik +1
The celebrated Takens' embedding theorem provides a theoretical foundation for reconstructing the full state of a dynamical system from partial observations. However, the classical…
AB-PINNs: Adaptive-Basis Physics-Informed Neural Networks for Residual-Driven Domain Decomposition
Jonah Botvinick-Greenhouse, Wael H. Ali, Mouhacine Benosman +1
We introduce adaptive-basis physics-informed neural networks (AB-PINNs), a novel approach to domain decomposition for training PINNs in which existing subdomains dynamically adapt…
Invariant Measures in Time-Delay Coordinates for Unique Dynamical System Identification
Jonah Botvinick-Greenhouse, Robert Martin, Yunan Yang
While invariant measures are widely employed to analyze physical systems when a direct study of pointwise trajectories is intractable, e.g., due to chaos or noise, they cannot uniq…
Invariant Measures for Data-Driven Dynamical System Identification: Analysis and Application
Jonah Botvinick-Greenhouse
We propose a novel approach for performing dynamical system identification, based upon the comparison of simulated and observed physical invariant measures. While standard methods…