Pith Number

pith:OPXDWCNM

pith:2026:OPXDWCNM7X4UVFEFCZQM4PDPKM

not attested not anchored not stored refs resolved

Turning Stale Gradients into Stable Gradients: Coherent Coordinate Descent with Implicit Landscape Smoothing for Lightweight Zeroth-Order Optimization

Chen Liang, Daniel Rakita, Qian Wang, Xiatao Sun

Coherent Coordinate Descent reuses historical gradients as warm starts to achieve O(1) query cost while keeping global descent directions in zeroth-order optimization.

arxiv:2605.14373 v1 · 2026-05-14 · cs.LG · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{OPXDWCNM7X4UVFEFCZQM4PDPKM}

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

CoCD is equivalent to Block Cyclic Coordinate Descent with warm starts, enabling O(1) query complexity per step while maintaining global descent directions; larger finite-difference step sizes induce implicit smoothing by reducing the effective smoothness constant.

C2weakest assumption

Historical gradients remain sufficiently coherent across iterations to provide reliable descent directions without significant landscape drift or loss of global information.

C3one line summary

CoCD converts stale gradients into stable descent directions for zeroth-order optimization through coherent coordinate updates and implicit landscape smoothing from larger finite-difference steps.

References

35 extracted · 35 resolved · 1 Pith anchors

[1] arXiv preprint arXiv:2504.18790 , year=

[2] IEEE Signal Processing Magazine , volume= 2020

[3] International Conference on Artificial Intelligence and Statistics , pages= 2018

[4] International Conference on Learning Representations , year=

[5] International Conference on Machine Learning , pages= 2018

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:07.804599Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

73ee3b09acfdf94a94851660ce3c6f531acbd98c406776752a89bb808c6d6732

Aliases

arxiv: 2605.14373 · arxiv_version: 2605.14373v1 · doi: 10.48550/arxiv.2605.14373 · pith_short_12: OPXDWCNM7X4U · pith_short_16: OPXDWCNM7X4UVFEF · pith_short_8: OPXDWCNM

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/OPXDWCNM7X4UVFEFCZQM4PDPKM \
  | 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: 73ee3b09acfdf94a94851660ce3c6f531acbd98c406776752a89bb808c6d6732

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9d4e3544c50b79d1b43ceae5aa1b66a308b0e3adb0da816190cc102fef8d78bf",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-14T04:52:24Z",
    "title_canon_sha256": "c3e3bab63ffae11e3e791827d4b003b1e730f4b04601a03d236eb04373780a25"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14373",
    "kind": "arxiv",
    "version": 1
  }
}