Pith Number

pith:XIRRZ4NE

pith:2026:XIRRZ4NEE3HHSLN2PE2NYWFFXC

not attested not anchored not stored refs resolved

IGT-OMD: Implicit Gradient Transport for Decision-Focused Learning under Delayed Feedback

Benjamin Amoh, Geoffrey G. Parker, Wesley Marrero

IGT-OMD corrects gradient staleness in delayed bilevel optimization by re-evaluating stale gradients at current parameters using stored inner solutions.

arxiv:2605.12693 v1 · 2026-05-12 · cs.LG

Open paper page JSON Open Graph Bundle Merged state What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{XIRRZ4NEE3HHSLN2PE2NYWFFXC}

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

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

IGT-OMD achieves the first sublinear regret bound for delayed bilevel optimization with queue-length-adaptive step sizes by reducing transport error from quadratic to linear dependence on delay.

C2weakest assumption

That inner solutions can be stored and re-evaluated at current parameters with negligible extra cost and that the bilevel problem satisfies the smoothness and convexity conditions needed for the regret analysis to go through.

C3one line summary

IGT-OMD reduces gradient transport error from quadratic to linear in delay length for delayed bilevel optimization and achieves sublinear regret with adaptive steps.

References

43 extracted · 43 resolved · 4 Pith anchors

[1] Adam N. Elmachtoub and Paul Grigas. Smart “Predict, then Optimize”.Management Science, 68(1):9–26, 2022. doi: 10.1287/mnsc.2020.3922 2022 · doi:10.1287/mnsc.2020.3922

[2] Melding the data-decisions pipeline: Decision- focused learning for combinatorial optimization 2019 · doi:10.1609/aaai.v33i01

[3] Decision-focused learning: Foundations, state of the art, benchmark and future opportunities.Journal of Artificial Intelligence Research, 81:1623–1701, 2024 2024

[4] Online learning under delayed feedback 2013

[5] Online learning and online convex optimization.Foundations and Trends in Machine Learning, 4(2):107–194 2012

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T03:09:49.807248Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

ba231cf1a426ce792dba7934dc58a5b8bc325ff69e04e34ddf6397a1f7f3359a

Aliases

arxiv: 2605.12693 · arxiv_version: 2605.12693v1 · doi: 10.48550/arxiv.2605.12693 · pith_short_12: XIRRZ4NEE3HH · pith_short_16: XIRRZ4NEE3HHSLN2 · pith_short_8: XIRRZ4NE

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/XIRRZ4NEE3HHSLN2PE2NYWFFXC \
  | 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: ba231cf1a426ce792dba7934dc58a5b8bc325ff69e04e34ddf6397a1f7f3359a

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "fe1830c9c21a32e1f45ed1ca7861ede2745fd967160ea4d2a4293a8bc4e8c61a",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-12T19:43:49Z",
    "title_canon_sha256": "fd8a84f7e0bd15919b058ff22f259f13ba9138e0daf6676e61b66a11a1568e4e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12693",
    "kind": "arxiv",
    "version": 1
  }
}