pith:Z76NZ7S3
On the Spectral Structure and Objective Equivalence of Orthogonal Multilabel Fisher Discriminants
All four multilabel Fisher objectives become equivalent under the total scatter constraint W^T S_t^{ML} W = I_r.
arxiv:2605.03283 v2 · 2026-05-05 · stat.ML · cs.AI · cs.LG
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{Z76NZ7S3NNZYXRE57NB66ZTSIM}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
All four Fisher objectives are equivalent under the W^T S_t^{ML} W = I_r constraint while the subspace estimation error admits a finite-sample O(k_max sqrt(d log d / n) / gap_r) bound with a matching Omega(sigma^2 d / (n gap_r)) minimax lower bound.
The data are generated from a linear label-effect model with sub-Gaussian noise; numerical checks use only synthetic data and serve as sanity verification rather than real-world validation.
Multilabel Fisher discriminants exhibit objective equivalence under total scatter normalization, with near-minimax optimal finite-sample subspace estimation rates under sub-Gaussian noise.
Receipt and verification
| First computed | 2026-06-30T01:18:18.596993Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
cffcdcfe5b6b738bc49dfb43ef66724315bdccf073eaff5ae651617faea0faa9
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/Z76NZ7S3NNZYXRE57NB66ZTSIM \
| 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: cffcdcfe5b6b738bc49dfb43ef66724315bdccf073eaff5ae651617faea0faa9
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "668762e9d149920598c29603ae3f945d4c402f88ef298fd2dc51d798fb60ec7d",
"cross_cats_sorted": [
"cs.AI",
"cs.LG"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "stat.ML",
"submitted_at": "2026-05-05T02:14:33Z",
"title_canon_sha256": "abd03bd0917a4c09bc85425e09fa0b9ddc28f18399a058ee25665df6afbae77e"
},
"schema_version": "1.0",
"source": {
"id": "2605.03283",
"kind": "arxiv",
"version": 2
}
}