pith:Z3MN3YHF
Adaptive Calibration in Non-Stationary Environments
Online algorithms achieve calibration errors that adapt to the unknown degree of non-stationarity in the outcome sequence.
arxiv:2605.11490 v2 · 2026-05-12 · cs.LG · stat.ML
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{Z3MN3YHFXKHP3KRB4ZZVHW4JA6}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
our algorithms attain Õ(√T+(TC)^{1/3}) for ℓ1 calibration error and Õ((1+C)^{1/3}) for both ℓ2 and pseudo KL calibration error. These bounds match the optimal rates in the stationary case (C=0) and recover known guarantees in the fully adversarial regime (C=T).
The non-stationarity of the environment can be captured by the minimal ℓ1 deviation C of mean outcomes, and epoch-based scheduling combined with a non-uniform partition of the prediction space suffices to achieve the stated adaptive bounds without knowledge of C.
Online algorithms achieve adaptive calibration bounds of Õ(√T + (TC)^{1/3}) for ℓ1 error and Õ((1+C)^{1/3}) for ℓ2 and pseudo-KL error, matching stationary and adversarial extremes via epoch scheduling and non-uniform prediction partitioning.
Cited by
Receipt and verification
| First computed | 2026-05-25T02:01:23.163616Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
ced8dde0e5ba8efdaa21e67353db8907813696aaf3f8b6be7e51ec7aaeafdc0b
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/Z3MN3YHFXKHP3KRB4ZZVHW4JA6 \
| 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: ced8dde0e5ba8efdaa21e67353db8907813696aaf3f8b6be7e51ec7aaeafdc0b
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "f77f7aa49fa0be81992d67f2e15b1ff58d58f26a49d88c3eb5d7b2fa3c8cfdde",
"cross_cats_sorted": [
"stat.ML"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-05-12T04:06:40Z",
"title_canon_sha256": "652bb2e580b68c23aa1ee55a250cbd1422f8e052e4e993dc37ef35be28587f49"
},
"schema_version": "1.0",
"source": {
"id": "2605.11490",
"kind": "arxiv",
"version": 2
}
}