Metraipolis › archive › dc_3896579d76ae

Canonical Layer Inference for Deep Gaussian Processes via Symmetry-Breaking Augmentation — arXiv:2610.23842

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.23842
License (as archived)
CC0-1.0
Archived
2026-10-19T09:37:42.393Z
SHA-256 of the archived text
270d102cc5d38143b980df2f66191046c4f7477e326d9a3304fe4a24e58b0677
Stable URL of this page
https://metraipolis.com/documento/dc_3896579d76ae

How to cite

Canonical Layer Inference for Deep Gaussian Processes via Symmetry-Breaking Augmentation — arXiv:2610.23842 — arXiv (en), https://arxiv.org/abs/2610.23842 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3896579d76ae (Metraipolis archive dc_3896579d76ae, sha256 270d102cc5d38143b980df2f66191046c4f7477e326d9a3304fe4a24e58b0677)
BibTeX
@misc{dc3896579d76ae,
  title = {Canonical Layer Inference for Deep Gaussian Processes via Symmetry-Breaking Augmentation — arXiv:2610.23842},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.23842},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3896579d76ae; sha256 270d102cc5d38143b980df2f66191046c4f7477e326d9a3304fe4a24e58b0677},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23842. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deep Gaussian processes (DGPs) are flexible priors for compositional regression functions, but inference for intermediate layers faces questions. The basic obstruction is an adjacent-layer symmetry: applying an invertible transformation and its inverse to two adjacent layers leaves the composed regression map unchanged. Under explicit symmetry and prior-comparability conditions, we show that the posterior may not concentrate on any prescribed intermediate-layer representation, even when the composed regression function is estimable. We then introduce an augmented $\rho$-fractional posterior that reweights layer decompositions by a non-saturating identity-deviation penalty. The augmentation changes posterior odds between symmetry-related decompositions by an exponential penalty ratio. Under proper choices of the penalty and a prior mass condition, it preserves function-level fractional posterior contraction, while shrinking the redundant layers towards the identity mapping. Thus, the likelihood does not identify a unique ``true'' set of layers; the augmentation favors identity-biased parsimonious decompositions within an equivalence class of layers; uniqueness of a selected representative is not established.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv stat.ME, nuovi lavori del giorno).
Categorie arXiv: Statistics Theory (math.ST) ; Methodology (stat.ME).
Pagina del lavoro: https://arxiv.org/abs/2610.23842 — 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 2026-10-19T09:32:59.751Z dalla pagina https://arxiv.org/list/stat.ME/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).