Sensitivity Analysis for Active Sampling, with Applications to the Simulation of Analog Circuits
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917664400605184 |
|---|---|
| author | Chhaibi, Reda Gamboa, Fabrice Oger, Christophe Oliveira, Vinicius Pellegrini, Clément Remot, Damien |
| author_facet | Chhaibi, Reda Gamboa, Fabrice Oger, Christophe Oliveira, Vinicius Pellegrini, Clément Remot, Damien |
| contents | We propose an active sampling flow, with the use-case of simulating the impact of combined variations on analog circuits. In such a context, given the large number of parameters, it is difficult to fit a surrogate model and to efficiently explore the space of design features.
By combining a drastic dimension reduction using sensitivity analysis and Bayesian surrogate modeling, we obtain a flexible active sampling flow. On synthetic and real datasets, this flow outperforms the usual Monte-Carlo sampling which often forms the foundation of design space exploration. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_07971 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Sensitivity Analysis for Active Sampling, with Applications to the Simulation of Analog Circuits Chhaibi, Reda Gamboa, Fabrice Oger, Christophe Oliveira, Vinicius Pellegrini, Clément Remot, Damien Machine Learning Applications Methodology We propose an active sampling flow, with the use-case of simulating the impact of combined variations on analog circuits. In such a context, given the large number of parameters, it is difficult to fit a surrogate model and to efficiently explore the space of design features. By combining a drastic dimension reduction using sensitivity analysis and Bayesian surrogate modeling, we obtain a flexible active sampling flow. On synthetic and real datasets, this flow outperforms the usual Monte-Carlo sampling which often forms the foundation of design space exploration. |
| title | Sensitivity Analysis for Active Sampling, with Applications to the Simulation of Analog Circuits |
| topic | Machine Learning Applications Methodology |
| url | https://arxiv.org/abs/2405.07971 |