Deep Legendre Transform
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911383682023424 |
|---|---|
| author | Minabutdinov, Aleksey Cheridito, Patrick |
| author_facet | Minabutdinov, Aleksey Cheridito, Patrick |
| contents | We introduce a novel deep learning algorithm for computing convex conjugates of differentiable convex functions, a fundamental operation in convex analysis with various applications in different fields such as optimization, control theory, physics and economics. While traditional numerical methods suffer from the curse of dimensionality and become computationally intractable in high dimensions, more recent neural network--based approaches scale better, but have mostly been studied with the aim of solving optimal transport problems and require the solution of complicated optimization or max--min problems. Using an implicit Fenchel formulation of convex conjugation, our approach facilitates an efficient gradient--based framework for the minimization of approximation errors and, as a byproduct, also provides a posteriori estimates of the approximation accuracy. Numerical experiments demonstrate our method's ability to deliver accurate results across different high-dimensional examples. Moreover, by employing symbolic regression with Kolmogorov--Arnold networks, it is able to obtain the exact convex conjugates of specific convex functions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_19649 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Deep Legendre Transform Minabutdinov, Aleksey Cheridito, Patrick Machine Learning Optimization and Control Primary 90C25, Secondary 68T07, 65K10, 35F21 I.2.6; G.1.6; I.5.1 We introduce a novel deep learning algorithm for computing convex conjugates of differentiable convex functions, a fundamental operation in convex analysis with various applications in different fields such as optimization, control theory, physics and economics. While traditional numerical methods suffer from the curse of dimensionality and become computationally intractable in high dimensions, more recent neural network--based approaches scale better, but have mostly been studied with the aim of solving optimal transport problems and require the solution of complicated optimization or max--min problems. Using an implicit Fenchel formulation of convex conjugation, our approach facilitates an efficient gradient--based framework for the minimization of approximation errors and, as a byproduct, also provides a posteriori estimates of the approximation accuracy. Numerical experiments demonstrate our method's ability to deliver accurate results across different high-dimensional examples. Moreover, by employing symbolic regression with Kolmogorov--Arnold networks, it is able to obtain the exact convex conjugates of specific convex functions. |
| title | Deep Legendre Transform |
| topic | Machine Learning Optimization and Control Primary 90C25, Secondary 68T07, 65K10, 35F21 I.2.6; G.1.6; I.5.1 |
| url | https://arxiv.org/abs/2512.19649 |