no code implementations • 6 Nov 2023 • Lingxiao Wang, Gert Aarts, Kai Zhou
This study delves into the connection between machine learning and lattice field theory by linking generative diffusion models (DMs) with stochastic quantization, from a stochastic differential equation perspective.
no code implementations • 29 Sep 2023 • Lingxiao Wang, Gert Aarts, Kai Zhou
In this work, we establish a direct connection between generative diffusion models (DMs) and stochastic quantization (SQ).
no code implementations • 10 Feb 2022 • Denis Boyda, Salvatore Calì, Sam Foreman, Lena Funcke, Daniel C. Hackett, Yin Lin, Gert Aarts, Andrei Alexandru, Xiao-Yong Jin, Biagio Lucini, Phiala E. Shanahan
There is great potential to apply machine learning in the area of numerical lattice quantum field theory, but full exploitation of that potential will require new strategies.
no code implementations • 29 Dec 2021 • Jamie Duell, Monika Seisenberger, Gert Aarts, ShangMing Zhou, Xiuyi Fan
In other words, although contribution towards a certain prediction is highlighted by feature attribution methods, the relation between features and the consequence of intervention is not studied.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI) +1
no code implementations • 21 Oct 2021 • Dimitrios Bachtis, Gert Aarts, Biagio Lucini
The transition to Euclidean space and the discretization of quantum field theories on spatial or space-time lattices opens up the opportunity to investigate probabilistic machine learning within quantum field theory.
no code implementations • 16 Sep 2021 • Dimitrios Bachtis, Gert Aarts, Biagio Lucini
The precise equivalence between discretized Euclidean field theories and a certain class of probabilistic graphical models, namely the mathematical framework of Markov random fields, opens up the opportunity to investigate machine learning from the perspective of quantum field theory.
no code implementations • 18 Feb 2021 • Dimitrios Bachtis, Gert Aarts, Biagio Lucini
We derive machine learning algorithms from discretized Euclidean field theories, making inference and learning possible within dynamics described by quantum field theory.
no code implementations • 29 Apr 2020 • Dimitrios Bachtis, Gert Aarts, Biagio Lucini
We propose the use of Monte Carlo histogram reweighting to extrapolate predictions of machine learning methods.