Scale-invariant Learning by Physics Inversion
Holl, Philipp, Koltun, Vladlen, Thuerey, Nils
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Oct-13-2022
- Country:
- North America > United States
- New Jersey (0.04)
- Pennsylvania > Philadelphia County
- Philadelphia (0.04)
- Europe
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- Germany > Bavaria
- Upper Bavaria > Munich (0.04)
- United Kingdom > England
- Asia > Middle East
- Israel (0.04)
- North America > United States
- Genre:
- Research Report (1.00)
- Industry:
- Education (0.66)
- Health & Medicine (0.46)
- Technology: