no code implementations • 2 Feb 2024 • Thomas D Swinburne, Danny Perez
The expected loss is an upper bound to the model generalization error which admits robust PAC-Bayes bounds for learning.
1 code implementation • 9 Jun 2023 • Van A. Ngo, Yen Ting Lin, Danny Perez
It has become common to perform kinetic analysis using approximate Koopman operators that transforms high-dimensional time series of observables into ranked dynamical modes.
no code implementations • 10 May 2022 • Yen Ting Lin, Yifeng Tian, Danny Perez, Daniel Livescu
We propose to adopt statistical regression as the projection operator to enable data-driven learning of the operators in the Mori--Zwanzig formalism.