Metraipolis › archive › dc_0fbc465635a7

Representation Learning for Exact Preimages — arXiv:2609.32018

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32018
License (as archived)
CC0-1.0
Archived
2026-10-07T22:36:13.736Z
SHA-256 of the archived text
0f48a35743f71fd63064397e2242c84cdbc8a1547b7a465e4a443b6c5e37d496
Stable URL of this page
https://metraipolis.com/documento/dc_0fbc465635a7

How to cite

Representation Learning for Exact Preimages — arXiv:2609.32018 — arXiv (en), https://arxiv.org/abs/2609.32018 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0fbc465635a7 (Metraipolis archive dc_0fbc465635a7, sha256 0f48a35743f71fd63064397e2242c84cdbc8a1547b7a465e4a443b6c5e37d496)
BibTeX
@misc{dc0fbc465635a7,
  title = {Representation Learning for Exact Preimages — arXiv:2609.32018},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32018},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0fbc465635a7; sha256 0f48a35743f71fd63064397e2242c84cdbc8a1547b7a465e4a443b6c5e37d496},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32018. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modern neural predictors can model highly nonlinear maps, but many scientific and engineering tasks require reasoning in the opposite direction: given a performance or safety level, the goal is to characterize the preimage, that is, the complete set of inputs which meet the desired target level and optimize over that set. For expressive neural predictors, however, such preimages typically have no explicit representation and are expensive to recover or optimize over. This creates a fundamental three-way challenge between expressive forward prediction, accurate preimage approximation, and tractable optimization over the preimage for downstream tasks. We introduce TRIO (tractable representations for preimage learning and inverse optimization), a framework for learning representations that make these objectives compatible by construction. Our key contribution is a preimage factorization: the forward model remains expressive through nonlinear radial transformations (including neural networks), while, under inversion, each transformation reduces to a single scalar radius, which yields simple geometric level sets. This yields an explicit geometric representation that is reusable for downstream optimization over the preimage, and, for linear objectives, we show that this admits a closed-form global solution. We finally prove a universal approximation theorem which shows that TRIO can approximate any continuous forward map and its entire family of potentially disconnected, nonconvex preimages arbitrarily well. Hence, TRIO combines expressive forward modeling, exact preimage recovery, and tractable global downstream optimization over preimages by design.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.32018 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T22:14:27.582Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).