PearSAN: A Machine Learning Method for Inverse Design using Pearson Correlated Surrogate Annealing
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917172584906752 |
|---|---|
| author | Bezick, Michael Wilson, Blake A. Iyer, Vaishnavi Chen, Yuheng Shalaev, Vladimir M. Kais, Sabre Kildishev, Alexander V. Boltasseva, Alexandra Lackey, Brad |
| author_facet | Bezick, Michael Wilson, Blake A. Iyer, Vaishnavi Chen, Yuheng Shalaev, Vladimir M. Kais, Sabre Kildishev, Alexander V. Boltasseva, Alexandra Lackey, Brad |
| contents | PearSAN is a machine learning-assisted optimization algorithm applicable to inverse design problems with large design spaces, where traditional optimizers struggle. The algorithm leverages the latent space of a generative model for rapid sampling and employs a Pearson correlated surrogate model to predict the figure of merit of the true design metric. As a showcase example, PearSAN is applied to thermophotovoltaic (TPV) metasurface design by matching the working bands between a thermal radiator and a photovoltaic cell. PearSAN can work with any pretrained generative model with a discretized latent space, making it easy to integrate with VQ-VAEs and binary autoencoders. Its novel Pearson correlational loss can be used as both a latent regularization method, similar to batch and layer normalization, and as a surrogate training loss. We compare both to previous energy matching losses, which are shown to enforce poor regularization and performance, even with upgraded affine parameters. PearSAN achieves a state-of-the-art maximum design efficiency of 97%, and is at least an order of magnitude faster than previous methods, with an improved maximum figure-of-merit gain. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_19284 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PearSAN: A Machine Learning Method for Inverse Design using Pearson Correlated Surrogate Annealing Bezick, Michael Wilson, Blake A. Iyer, Vaishnavi Chen, Yuheng Shalaev, Vladimir M. Kais, Sabre Kildishev, Alexander V. Boltasseva, Alexandra Lackey, Brad Machine Learning Artificial Intelligence PearSAN is a machine learning-assisted optimization algorithm applicable to inverse design problems with large design spaces, where traditional optimizers struggle. The algorithm leverages the latent space of a generative model for rapid sampling and employs a Pearson correlated surrogate model to predict the figure of merit of the true design metric. As a showcase example, PearSAN is applied to thermophotovoltaic (TPV) metasurface design by matching the working bands between a thermal radiator and a photovoltaic cell. PearSAN can work with any pretrained generative model with a discretized latent space, making it easy to integrate with VQ-VAEs and binary autoencoders. Its novel Pearson correlational loss can be used as both a latent regularization method, similar to batch and layer normalization, and as a surrogate training loss. We compare both to previous energy matching losses, which are shown to enforce poor regularization and performance, even with upgraded affine parameters. PearSAN achieves a state-of-the-art maximum design efficiency of 97%, and is at least an order of magnitude faster than previous methods, with an improved maximum figure-of-merit gain. |
| title | PearSAN: A Machine Learning Method for Inverse Design using Pearson Correlated Surrogate Annealing |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2412.19284 |