Timezone: »
Score Matching via Differentiable Physics
Benjamin Holzschuh · Simona Vegetti · Nils Thuerey
Diffusion models based on stochastic differential equations (SDEs) gradually perturb a data distribution $p(\mathbf{x})$ over time by adding noise to it. A neural network is trained to approximate the score $\nabla_\mathbf{x} \log p_t(\mathbf{x})$ at time $t$, which can be used to reverse the corruption process. In this paper, we focus on learning the score field that is associated with the time evolution according to a physics operator in the presence of natural non-deterministic physical processes like diffusion. A decisive difference to previous methods is that the SDE underlying our approach transforms the state of a physical system to another state at a later time. For that purpose, we replace the drift of the underlying SDE formulation with a differentiable simulator or a neural network approximation of the physics. At the core of our method, we optimize the so-called probability flow ODE to fit a training set of simulation trajectories inside an ODE solver and solve the reverse-time SDE for inference to sample plausible trajectories that evolve towards a given end state.
Author Information
Benjamin Holzschuh (Technical University Munich, Max-Planck Institute for Astrophysics)
Simona Vegetti (Max Planck Institute for Astrophysics)
Nils Thuerey (Technical University of Munich)
More from the Same Authors
-
2022 : Leveraging the Stochastic Predictions of Bayesian Neural Networks for Fluid Simulations »
Maximilian Mueller · Robin Greif · Frank Jenko · Nils Thuerey -
2022 : Learning Similarity Metrics for Volumetric Simulations with Multiscale CNNs »
Georg Kohl · Liwei Chen · Nils Thuerey -
2022 Poster: Scale-invariant Learning by Physics Inversion »
Philipp Holl · Vladlen Koltun · Nils Thuerey -
2022 Poster: Guaranteed Conservation of Momentum for Learning Particle-based Fluid Dynamics »
Lukas Prantl · Benjamin Ummenhofer · Vladlen Koltun · Nils Thuerey -
2022 Poster: ULNeF: Untangled Layered Neural Fields for Mix-and-Match Virtual Try-On »
Igor Santesteban · Miguel Otaduy · Nils Thuerey · Dan Casas -
2021 : Nils Thuerey »
Nils Thuerey -
2020 : Liwei Chen - Deep Learning Surrogates for Computational Fluid Dynamics »
Nils Thuerey -
2020 : Nils Thuerey - Lead the Way! Deep Learning via Differentiable Simulations »
Nils Thuerey -
2020 : Oral 01: phiflow - A differentiable PDE solving framework for deep learning via physical simulations »
Nils Thuerey -
2020 Poster: Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers »
Kiwon Um · Robert Brand · Yun (Raymond) Fei · Philipp Holl · Nils Thuerey -
2019 : Morning Coffee Break & Poster Session »
Eric Metodiev · Keming Zhang · Markus Stoye · Randy Churchill · Soumalya Sarkar · Miles Cranmer · Johann Brehmer · Danilo Jimenez Rezende · Peter Harrington · AkshatKumar Nigam · Nils Thuerey · Lukasz Maziarka · Alvaro Sanchez Gonzalez · Atakan Okan · James Ritchie · N. Benjamin Erichson · Harvey Cheng · Peihong Jiang · Seong Ho Pahng · Samson Koelle · Sami Khairy · Adrian Pol · Rushil Anirudh · Jannis Born · Benjamin Sanchez-Lengeling · Brian Timar · Rhys Goodall · Tamás Kriváchy · Lu Lu · Thomas Adler · Nathaniel Trask · Noëlie Cherrier · Tomohiko Konno · Muhammad Kasim · Tobias Golling · Zaccary Alperstein · Andrei Ustyuzhanin · James Stokes · Anna Golubeva · Ian Char · Ksenia Korovina · Youngwoo Cho · Chanchal Chatterjee · Tom Westerhout · Gorka Muñoz-Gil · Juan Zamudio-Fernandez · Jennifer Wei · Brian Lee · Johannes Kofler · Bruce Power · Nikita Kazeev · Andrey Ustyuzhanin · Artem Maevskiy · Pascal Friederich · Arash Tavakoli · Willie Neiswanger · Bohdan Kulchytskyy · sindhu hari · Paul Leu · Paul Atzberger -
2018 : Coffee Break 1 (Posters) »
Ananya Kumar · Siyu Huang · Huazhe Xu · Michael Janner · Parth Chadha · Nils Thuerey · Peter Lu · Maria Bauza · Anthony Tompkins · Guanya Shi · Thomas Baumeister · André Ofner · Zhi-Qi Cheng · Yuping Luo · Deepika Bablani · Jeroen Vanbaar · Kartic Subr · Tatiana López-Guevara · Devesh Jha · Fabian Fuchs · Stefano Rosa · Alison Pouplin · Alex Ray · Qi Liu · Eric Crawford