
AM
Alejandro Moreno Arcas
· 1 min read
ResearcharXiv cs.LG
Func-JEPA: Learning a Sobolev Space of Functions as Latent Vectors
arXiv:2611.19542v1 Announce Type: new
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.
Original source
This story was published by arXiv cs.LG and written by Alejandro Moreno Arcas. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


