Timezone: »

 
Poster
Scale-invariant Learning by Physics Inversion
Philipp Holl · Vladlen Koltun · Nils Thuerey

Thu Dec 01 02:00 PM -- 04:00 PM (PST) @ Hall J #904
in Poster Session 6 »

Solving inverse problems, such as parameter estimation and optimal control, is a vital part of science. Many experiments repeatedly collect data and rely on machine learning algorithms to quickly infer solutions to the associated inverse problems. We find that state-of-the-art training techniques are not well-suited to many problems that involve physical processes. The highly nonlinear behavior, common in physical processes, results in strongly varying gradients that lead first-order optimizers like SGD or Adam to compute suboptimal optimization directions.We propose a novel hybrid training approach that combines higher-order optimization methods with machine learning techniques. We take updates from a scale-invariant inverse problem solver and embed them into the gradient-descent-based learning pipeline, replacing the regular gradient of the physical process.We demonstrate the capabilities of our method on a variety of canonical physical systems, showing that it yields significant improvements on a wide range of optimization and learning problems.

Keywords: Inverse Problems · Neural Networks · physical simulations · Higher-order Optimization
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Philipp Holl (Technical University of Munich)
Vladlen Koltun (Apple)
Nils Thuerey (Technical University of Munich)

More from the Same Authors