pith:Q4AMPNU5
Bayesian online learning in the one-pass regime: Frequentist validity and uncertainty quantification
A Bayesian algorithm for one-pass online learning achieves optimal posterior convergence and an online Bernstein-von Mises theorem.
arxiv:2604.27442 v2 · 2026-04-30 · math.ST · stat.ML · stat.TH
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{Q4AMPNU5KYXMJCSZ6TPV4I2BXS}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
For this algorithm, we show that the sequentially updated posterior attains the optimal convergence rate. Building on this, we establish an online analogue of the Bernstein-von Mises theorem, which guarantees valid uncertainty quantification without diverging mini-batch sample sizes.
The analysis assumes that a warm-start phase can be incorporated to ensure stable sequential updates in the one-pass regime without violating the single-pass constraint or requiring additional conditions that may not hold for general data streams.
A one-pass Bayesian online learner with warm-start achieves optimal posterior convergence and satisfies an online Bernstein-von Mises theorem for uncertainty quantification.
Receipt and verification
| First computed | 2026-06-11T01:09:36.571493Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
8700c7b69d562ec48a59f4df5e2341bcb08d22352d974d6ba751f97729f773b0
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/Q4AMPNU5KYXMJCSZ6TPV4I2BXS \
| 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: 8700c7b69d562ec48a59f4df5e2341bcb08d22352d974d6ba751f97729f773b0
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "c52da6ac5ca8b93c632b6dcbb546e27924dccc2ffeae31588d763db780edd4f0",
"cross_cats_sorted": [
"stat.ML",
"stat.TH"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "math.ST",
"submitted_at": "2026-04-30T05:29:06Z",
"title_canon_sha256": "f45db0a01905c0764b6d6c64779a2956ea26c73ef25365783754f7ba3bb7c606"
},
"schema_version": "1.0",
"source": {
"id": "2604.27442",
"kind": "arxiv",
"version": 2
}
}