pith. sign in
Pith Number

pith:X3WYPJSN

pith:2026:X3WYPJSN2SXZXKYZEGQATEHETN
not attested not anchored not stored refs resolved

A Regret Perspective on Online Multiple Testing

Fang Kong, Hongxin Wei, Kongchang Zhou, Qingyang Hao

Deterministic online FDR control forces linear regret from early threshold depletion, but a history-decoupled non-negative perturbation reduces it to order sqrt(T) without adding false negatives.

arxiv:2605.13916 v1 · 2026-05-13 · stat.ML · cs.AI · cs.LG

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{X3WYPJSN2SXZXKYZEGQATEHETN}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open
Portable graph bundle live · download bundle · merged state
The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

We prove the Duality of Regret Conservation: purely deterministic procedures ensuring strict FDR control inevitably incur an Ω(T) linear regret penalty, as threshold depletion during signal-sparse cold starts forces massive false negatives. Tailored for exogenous testing streams, we propose Decoupled-OMT (DOMT) ... yields an order-optimal Ω(√T) regret reduction in bursty environments.

C2weakest assumption

The analysis assumes exogenous testing streams (decisions do not affect future data generation) and stationarity for the asymptotic safety guarantee; the finite-sample bounds during cold starts rely on the perturbation being strictly non-negative and history-decoupled without introducing additional false negatives.

C3one line summary

The paper proves that deterministic FDR-controlling procedures incur linear regret in online multiple testing and introduces DOMT, a perturbation-based meta-wrapper that reduces regret to order-optimal sublinear levels while preserving safety.

References

53 extracted · 53 resolved · 0 Pith anchors

[1] Conformal risk control 2024
[2] Online local false discovery rate control: A resource allocation approach.CoRR, abs/2402.11425, 2024 2024
[3] Cap: A general algorithm for online selective conformal prediction with fcr control.Journal of Machine Learning Research, 26(287):1–74, 2025 2025
[4] Practical adversarial multivalid conformal prediction 2022
[5] Stephen Bates, Anastasios Nikolas Angelopoulos, Lihua Lei, Jitendra Malik, and Michael I. Jordan. Distribution-free, risk-controlling prediction sets.J. ACM, 68:43:1–43:34, 2021 2021
Receipt and verification
First computed 2026-05-17T23:39:18.751066Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

beed87a64dd4af9bab1921a00990e49b668240606aba23dac39f90d2cca89664

Aliases

arxiv: 2605.13916 · arxiv_version: 2605.13916v1 · doi: 10.48550/arxiv.2605.13916 · pith_short_12: X3WYPJSN2SXZ · pith_short_16: X3WYPJSN2SXZXKYZ · pith_short_8: X3WYPJSN
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/X3WYPJSN2SXZXKYZEGQATEHETN \
  | 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: beed87a64dd4af9bab1921a00990e49b668240606aba23dac39f90d2cca89664
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "0a72bf129f9fcc43b95413c7a12df584f826cb1bc73888f95cfb73cdfffde59a",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "stat.ML",
    "submitted_at": "2026-05-13T10:42:46Z",
    "title_canon_sha256": "3fffb58557f8af3b518e2baac858b9548c7e512c5833b67f5d92f5355d137a5a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13916",
    "kind": "arxiv",
    "version": 1
  }
}