pith:NI5DRLRS
Universal Approximation of Nonlinear Operators and Their Derivatives
Nonlinear k-times differentiable operators between Banach spaces and their derivatives can be universally approximated by operator learning architectures.
arxiv:2605.15285 v1 · 2026-05-14 · cs.LG · cs.AI · cs.NA · math.FA · math.NA · math.OC
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{NI5DRLRS7XEZLDUE2FQPCE5HFN}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
We prove the first UATs of non-linear k-times differentiable operators between Banach spaces and their derivatives, uniformly on compact sets and in weighted Sobolev norms for general finite input measures, via OL architectures. Our results are the first complete generalizations of the corresponding influential classical results in [Hornik, 1991] to infinite-dimensional settings and OL.
The proofs depend on k-times continuous differentiability in the sense of Bastiani together with the construction of novel weighted Sobolev spaces and the choice of natural compact-open topologies; if these specific choices fail to capture the intended class of operators or if the approximation properties of Banach spaces do not hold in the required uniform sense, the claimed UATs would not follow.
Proves the first universal approximation theorems for k-times differentiable nonlinear operators between Banach spaces and their derivatives uniformly on compact sets in weighted Sobolev norms via encoder-decoder operator learning architectures.
References
Formal links
Receipt and verification
| First computed | 2026-05-20T00:00:50.656417Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
6a3a38ae32fdc9958e84d160f113a72b68e9418043bfc58c533fd60e60758bf3
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/NI5DRLRS7XEZLDUE2FQPCE5HFN \
| jq -c '.canonical_record' \
| python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 6a3a38ae32fdc9958e84d160f113a72b68e9418043bfc58c533fd60e60758bf3
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "e877eb111a1ad47ab660c3667a7722521db2ea754596af55305fc2f0288669a2",
"cross_cats_sorted": [
"cs.AI",
"cs.NA",
"math.FA",
"math.NA",
"math.OC"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-05-14T18:00:58Z",
"title_canon_sha256": "3d09e69b54d193e638a2b92a97433eeb092be5bf31ebf4b93b10669f950cda8c"
},
"schema_version": "1.0",
"source": {
"id": "2605.15285",
"kind": "arxiv",
"version": 1
}
}