activity
20172026
most citedExtended dynamic mode decomposition with dictionary learning: a data-driven adaptive spectral decomposition of the Koopman operator

449 citations · 489 across the 7 of their papers we have counts for

collaborators

10 papers

math.NA2026

Rational neural networks for tracking complex singularities of nonlinear PDEs

Nadiia Derevianko, Hans-Joachim Bungartz, Felix Dietrich

We present a neural network-based method for numerical analytic continuation of solutions of nonlinear partial differential equations (PDEs) and detection of their complex singular…

math.NA2025

Neural network-based singularity detection and applications

Nadiia Derevianko, Ioannis G. Kevrekidis, Felix Dietrich

We present a method for constructing a special type of shallow neural network that learns univariate meromorphic functions with pole-type singularities. Our method is based on usin…

stat.ML20213 cited

On the Correspondence between Gaussian Processes and Geometric Harmonics

Felix Dietrich, Juan M. Bello-Rivas, Ioannis G. Kevrekidis

We discuss the correspondence between Gaussian process regression and Geometric Harmonics, two similar kernel-based methods that are typically used in different contexts. Research…

nlin.AO20202 cited

Learning emergent PDEs in a learned emergent space

Felix P. Kemeth, Tom Bertalan, Thomas Thiem +4

We extract data-driven, intrinsic spatial coordinates from observations of the dynamics of large systems of coupled heterogeneous agents. These coordinates then serve as an emergen…

cs.LG2020

Transformations between deep neural networks

Tom Bertalan, Felix Dietrich, Ioannis G. Kevrekidis

We propose to test, and when possible establish, an equivalence between two different artificial neural networks by attempting to construct a data-driven transformation between the…

physics.data-an2019

A geometric approach to the transport of discontinuous densities

Caroline Moosmüller, Felix Dietrich, Ioannis G. Kevrekidis

Different observations of a relation between inputs ("sources") and outputs ("targets") are often reported in terms of histograms (discretizations of the source and the target dens…