Compact neural networks for astronomy with optimal transport bias correction
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914168165105664 |
|---|---|
| author | Wang, Shuhuan Xie, Yuzhen Li, Jiayi |
| author_facet | Wang, Shuhuan Xie, Yuzhen Li, Jiayi |
| contents | Astronomical imaging confronts an efficiency-resolution tradeoff that limits large-scale morphological classification and redshift prediction. We introduce WaveletMamba, a theory-driven framework integrating wavelet decomposition with state-space modeling, mathematical regularization, and multi-level bias correction. WaveletMamba achieves 81.72% +/- 0.53% classification accuracy at 64x64 resolution with only 3.54M parameters, delivering high-resolution performance (80.93% +/- 0.27% at 244x244) at low-resolution inputs with 9.7x computational efficiency gains. The framework exhibits Resolution Multistability, where models trained on low-resolution data achieve consistent accuracy across different input scales despite divergent internal representations. The framework's multi-level bias correction synergizes HK distance (distribution-level optimal transport) with Color-Aware Weighting (sample-level fine-tuning), achieving 22.96% Log-MSE improvement and 26.10% outlier reduction without explicit selection function modeling. Here, we show that mathematical rigor enables unprecedented efficiency and comprehensive bias correction in scientific AI, bridging computer vision and astrophysics to revolutionize interdisciplinary scientific discovery. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_18139 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Compact neural networks for astronomy with optimal transport bias correction Wang, Shuhuan Xie, Yuzhen Li, Jiayi Computer Vision and Pattern Recognition 68T05, 49Q22, 62J12 I.2.6; I.5.4; J.2 Astronomical imaging confronts an efficiency-resolution tradeoff that limits large-scale morphological classification and redshift prediction. We introduce WaveletMamba, a theory-driven framework integrating wavelet decomposition with state-space modeling, mathematical regularization, and multi-level bias correction. WaveletMamba achieves 81.72% +/- 0.53% classification accuracy at 64x64 resolution with only 3.54M parameters, delivering high-resolution performance (80.93% +/- 0.27% at 244x244) at low-resolution inputs with 9.7x computational efficiency gains. The framework exhibits Resolution Multistability, where models trained on low-resolution data achieve consistent accuracy across different input scales despite divergent internal representations. The framework's multi-level bias correction synergizes HK distance (distribution-level optimal transport) with Color-Aware Weighting (sample-level fine-tuning), achieving 22.96% Log-MSE improvement and 26.10% outlier reduction without explicit selection function modeling. Here, we show that mathematical rigor enables unprecedented efficiency and comprehensive bias correction in scientific AI, bridging computer vision and astrophysics to revolutionize interdisciplinary scientific discovery. |
| title | Compact neural networks for astronomy with optimal transport bias correction |
| topic | Computer Vision and Pattern Recognition 68T05, 49Q22, 62J12 I.2.6; I.5.4; J.2 |
| url | https://arxiv.org/abs/2511.18139 |