A Transformer Model for Symbolic Regression towards Scientific Discovery
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912175687204864 |
|---|---|
| author | Lalande, Florian Matsubara, Yoshitomo Chiba, Naoya Taniai, Tatsunori Igarashi, Ryo Ushiku, Yoshitaka |
| author_facet | Lalande, Florian Matsubara, Yoshitomo Chiba, Naoya Taniai, Tatsunori Igarashi, Ryo Ushiku, Yoshitaka |
| contents | Symbolic Regression (SR) searches for mathematical expressions which best describe numerical datasets. This allows to circumvent interpretation issues inherent to artificial neural networks, but SR algorithms are often computationally expensive. This work proposes a new Transformer model aiming at Symbolic Regression particularly focused on its application for Scientific Discovery. We propose three encoder architectures with increasing flexibility but at the cost of column-permutation equivariance violation. Training results indicate that the most flexible architecture is required to prevent from overfitting. Once trained, we apply our best model to the SRSD datasets (Symbolic Regression for Scientific Discovery datasets) which yields state-of-the-art results using the normalized tree-based edit distance, at no extra computational cost. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_04070 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | A Transformer Model for Symbolic Regression towards Scientific Discovery Lalande, Florian Matsubara, Yoshitomo Chiba, Naoya Taniai, Tatsunori Igarashi, Ryo Ushiku, Yoshitaka Machine Learning Symbolic Regression (SR) searches for mathematical expressions which best describe numerical datasets. This allows to circumvent interpretation issues inherent to artificial neural networks, but SR algorithms are often computationally expensive. This work proposes a new Transformer model aiming at Symbolic Regression particularly focused on its application for Scientific Discovery. We propose three encoder architectures with increasing flexibility but at the cost of column-permutation equivariance violation. Training results indicate that the most flexible architecture is required to prevent from overfitting. Once trained, we apply our best model to the SRSD datasets (Symbolic Regression for Scientific Discovery datasets) which yields state-of-the-art results using the normalized tree-based edit distance, at no extra computational cost. |
| title | A Transformer Model for Symbolic Regression towards Scientific Discovery |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2312.04070 |