Pith Number

pith:AXKUHAXY

pith:2026:AXKUHAXYN45PAUS3XSNGLLZABM

not attested not anchored not stored refs resolved

Winning Lottery Tickets in Neural Networks via a Quantum-Inspired Classical Algorithm

Hayata Yamasaki, Mio Murao, Natsuto Isogai, Sho Sonoda

A classical algorithm samples from a ridgelet-defined distribution to select sparse neural subnetworks in polynomial time in data dimension D.

arxiv:2605.13979 v1 · 2026-05-13 · quant-ph · cs.LG · stat.ML

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{AXKUHAXYN45PAUS3XSNGLLZABM}

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 show that our algorithm runs in time O(poly(D)), thereby removing the exponential dependence on D from the previous classical approach.

C2weakest assumption

The ridgelet transform defines an optimized probability distribution that admits an efficient classical sampling procedure with only polynomial dependence on the data dimension D.

C3one line summary

A classical polynomial-time algorithm for optimized sampling of lottery tickets in neural networks removes the exponential dependence on data dimension from prior classical approaches.

References

33 extracted · 33 resolved · 3 Pith anchors

[1] Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding 2016 · arXiv:1510.00149

[2] SNIP: SINGLE-SHOT NETWORK PRUNING BASED ON CONNECTION SENSITIVITY 2019

[3] Hidenori Tanaka, Daniel Kunin, Daniel L. K. Yamins, and Surya Ganguli. Pruning neural networks without any data by iteratively conserving synaptic flow. InProceedings of the 34th International Confere 2020

[4] Rigging the lottery: making all tickets winners 2020

[5] The lottery ticket hypothesis: Finding sparse, trainable neural networks 2019

Receipt and verification

First computed	2026-05-17T23:39:13.397630Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

05d54382f86f3af0525bbc9a65af200b2661f26e02e507b3408e766395b3695f

Aliases

arxiv: 2605.13979 · arxiv_version: 2605.13979v1 · doi: 10.48550/arxiv.2605.13979 · pith_short_12: AXKUHAXYN45P · pith_short_16: AXKUHAXYN45PAUS3 · pith_short_8: AXKUHAXY

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/AXKUHAXYN45PAUS3XSNGLLZABM \
  | 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: 05d54382f86f3af0525bbc9a65af200b2661f26e02e507b3408e766395b3695f

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "38bd54ce92d4d4b20af1ef795ef72a3dac349e3f99d6868013d166a7de00c4c0",
    "cross_cats_sorted": [
      "cs.LG",
      "stat.ML"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "quant-ph",
    "submitted_at": "2026-05-13T18:00:56Z",
    "title_canon_sha256": "776852bf12ce2a958cddb35115074cf35b13dc06db0777fda00e7c12eedef9c5"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13979",
    "kind": "arxiv",
    "version": 1
  }
}