SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.10131 · ICLR · 2022

Half-Inverse Gradients for Physical Deep Learning

Nils Thuerey, Patrick Schnell

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 5 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
tum-pbs/half-inverse-gradients canonical 2 of 2
tum-pbs/PhiFlow canonical 0 of 3
FunctionStatusWhere it lives
NLO_optimization_framework Ran tum-pbs/half-inverse-gradients/Nonlinear_oscillators/NLO_HIG.py
code served (permissive licence) · get_code("00b52f87ad855c71")
timing_dec Ran tum-pbs/half-inverse-gradients/Nonlinear_oscillators/NLO_HIG.py
code served (permissive licence) · get_code("8639882900729fb4")
construct_orifice3d Not yet run tum-pbs/PhiFlow/demos/Top_Opt/geom.py
code served (permissive licence) · get_code("c6eaee4d81ccfb3b")
to_phi_t Not yet run tum-pbs/PhiFlow/demos/Top_Opt/geom.py
code served (permissive licence) · get_code("3c7b260d9f6dbef3")
to_torch_t Not yet run tum-pbs/PhiFlow/demos/Top_Opt/geom.py
code served (permissive licence) · get_code("b4c8870cc461fe56")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recent works in deep learning have shown that integrating differentiable physics simulators into the training process can greatly improve the quality of results. Although this combination represents a more complex optimization task than supervised neural network training, the same gradient-based optimizers are typically employed to minimize the loss function. However, the integrated physics solvers have a profound effect on the gradient flow as manipulating scales in magnitude and direction is an inherent property of many physical processes. Consequently, the gradient flow is often highly unbalanced and creates an environment in which existing gradient-based optimizers perform poorly. In this work, we analyze the characteristics of both physical and neural network optimizations to derive a new method that does not suffer from this phenomenon. Our method is based on a halfinversion of the Jacobian and combines principles of both classical network and physics optimizers to solve the combined optimization task. Compared to state-ofthe-art neural network optimizers, our method converges more quickly and yields better solutions, which we demonstrate on three complex learning problems involving nonlinear oscillators, the Schrödinger equation and the Poisson problem.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.10131")
get_code_for_paper("2203.10131")
have("2203.10131")

Connect an agent — have() is free.