Metraipolis › archive › dc_3ee1fdc323ce
Exact ReLU realization of binary affine refinement iterates via reflection folding and cone switching — arXiv:2609.11962
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.11962
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T03:15:59.685Z
- SHA-256 of the archived text
37a20e3d4134b721b7ecb82a837e0ededebd1e8cc0c26a502e8882b0aa13cfab- Stable URL of this page
https://metraipolis.com/documento/dc_3ee1fdc323ce
How to cite
Exact ReLU realization of binary affine refinement iterates via reflection folding and cone switching — arXiv:2609.11962 — arXiv (en), https://arxiv.org/abs/2609.11962 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3ee1fdc323ce (Metraipolis archive dc_3ee1fdc323ce, sha256 37a20e3d4134b721b7ecb82a837e0ededebd1e8cc0c26a502e8882b0aa13cfab)
BibTeX
@misc{dc3ee1fdc323ce,
title = {Exact ReLU realization of binary affine refinement iterates via reflection folding and cone switching — arXiv:2609.11962},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.11962},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3ee1fdc323ce; sha256 37a20e3d4134b721b7ecb82a837e0ededebd1e8cc0c26a502e8882b0aa13cfab},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11962. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study vector-valued binary affine refinement operators with finitely supported matrix masks and compactly supported continuous piecewise linear input and forcing data. We prove that every finite refinement iterate admits an exact ReLU realization of fixed width and depth linear in the number of iterations. No separation of the forcing profile from the binary cell seams is required. The main mechanism is universal reflection doubling. Pairing each residual profile with its reflection replaces the two binary transition matrices by one fixed block matrix together with a fixed swap involution. The cell-seam identity makes the two branch candidates agree at the tent fold, while their swap-odd component is bounded linearly by the distance to the fold. This permits exact branch selection by a fixed continuous piecewise linear cone switch, without multiplication by a variable selector. The resulting primal recursion requires the residual orbit in reverse order. We obtain exact backward replay from the residual memory controller developed previously for affine refinement, interpreted here through the reflection quotient of circle doubling. The construction propagates the full vectorized profiles rather than decomposing the input and forcing into reference atoms. We also treat stage-dependent forcing from a fixed finite-dimensional family and show that genuine reflection equivariance reduces the doubled cascade to a single parity sector. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.LG). Categorie arXiv: Optimization and Control (math.OC) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.11962 — 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 2026-10-16T03:05:44.093Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).