Abstract: A computationally efficient method for the automation of inverse design in science and engineering is introduced. Based on simple least-square regression, the method leverages the dynamic mode decomposition algorithm in order to construct a low-rank subspace spanning multiple geometric representations in a latent embedding space. The proposed inverse design dynamic mode composition (ID-DMD) algorithm leverages the computed low-dimensional subspace to enable fast digital design and optimization of geometry on laptop-level computing, including the potential to prescribe the dynamics themselves through reduced order models. Moreover, the method is robust to noise, physically interpretable, and can provide uncertainty quantification metrics. The architecture can also efficiently scale to large-scale design problems using randomized algorithms in the ID-DMD. The simplicity of the method and its implementation are highly attractive in practice, and the ID-DMD has been demonstrated to be an order of magnitude more accurate than competing methods while simultaneously being 3-5 orders faster on challenging engineering design problems ranging from structural vibrations to fluid dynamics. Due to its speed, robustness, interpretability, and ease-of-use, ID-DMD in comparison with other leading machine learning methods represents a significant advancement in data-driven methods for inverse design and optimization, promising a paradigm shift in how to approach inverse design in practice.
3:30pm - Pre-talk meet and greet teatime - 219 Prospect Street, 13th floor, there will be light snacks and beverages in the kitchen area.
