34 citations · 162 across the 24 of their papers we have counts for
24 papers
Universality of physical neural networks with multivariate nonlinearity
Benjamin Savinson, David J. Norris, Siddhartha Mishra +1
The enormous energy demand of artificial intelligence is driving the development of alternative hardware for deep learning. Physical neural networks try to exploit physical systems…
Towards a Certificate of Trust: Task-Aware OOD Detection for Scientific AI
Bogdan Raonić, Siddhartha Mishra, Samuel Lanthaler
Data-driven models are increasingly adopted in critical scientific fields like weather forecasting and fluid dynamics. These methods can fail on out-of-distribution (OOD) data, but…
Theory-to-Practice Gap for Neural Networks and Neural Operators
Philipp Grohs, Samuel Lanthaler, Margaret Trautner
This work studies the sampling complexity of learning with ReLU neural networks and neural operators. For mappings belonging to relevant approximation spaces, we derive upper bound…
Generative AI for fast and accurate statistical computation of fluids
Roberto Molinaro, Samuel Lanthaler, Bogdan Raonić +9
We present a generative AI algorithm for addressing the pressing task of fast, accurate, and robust statistical computation of three-dimensional turbulent fluid flows. Our algorith…
Operator Learning of Lipschitz Operators: An Information-Theoretic Perspective
Samuel Lanthaler
Operator learning based on neural operators has emerged as a promising paradigm for the data-driven approximation of operators, mapping between infinite-dimensional Banach spaces.…
Data Complexity Estimates for Operator Learning
Nikola B. Kovachki, Samuel Lanthaler, Hrushikesh Mhaskar
Operator learning has emerged as a new paradigm for the data-driven approximation of nonlinear operators. Despite its empirical success, the theoretical underpinnings governing the…