arXiv · 2611.19542
Func-JEPA: Learning a Sobolev Space of Functions as Latent Vectors
Abstract
Pretraining an encoder once and reusing it across tasks is a widespread approach in vision and language. However, neural symbolic mathematics still trains a dedicated sequence-to-sequence model for each task, so that no representation of a function is shared. In this work, we propose the Function Joint-Embedding Predictive Architecture (Func-JEPA, abbreviated f-JEPA): an encoder of mathematical functions, pretrained on their symbolic form, whose latent space imitates the Sobolev space H^1 and in which differentiation is a learned latent operator. The norm of a latent is computed exactly from the function, whereas its direction is learned to match Sobolev angles. The frozen encoder is then reused by lightweight modules for decoding, composition, integration, and regression from samples. The representation and four downstream tasks are evaluated within and outside the pretraining distribution. f-JEPA recovers exact formulas from noisy samples more often than the compared symbolic-regression methods, whereas computer algebra and task-specific models remain stronger on standard integration and differential-equation benchmarks.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Alejandro Moreno Arcas. 2026-11-14. Func-JEPA: Learning a Sobolev Space of Functions as Latent Vectors. https://searcharxiv.com/abs/2611.19542
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.