pith:BEFQERO5
DiVeQ: Differentiable Vector Quantization Using the Reparameterization Trick
DiVeQ makes vector quantization differentiable by reparameterizing it as an additive error vector.
arxiv:2509.26469 v4 · 2025-09-30 · cs.LG
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{BEFQERO5LHCFQBA2YFUJCYKAMS}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
In VQ-VAE image compression, VQGAN image generation, and DAC speech coding tasks across various data sets, our proposed methods improve reconstruction and sample quality over alternative quantization approaches.
That modeling quantization distortion as an additive error vector (and the space-filling curve assignment) produces gradients that are both stable and unbiased enough to replace auxiliary losses and temperature schedules without degrading the hard forward-pass behavior.
DiVeQ and SF-DiVeQ make vector quantization differentiable through error-vector reparameterization and space-filling curves, yielding better reconstruction in VQ-VAE, VQGAN, and DAC tasks.
Formal links
Receipt and verification
| First computed | 2026-05-27T01:05:38.245132Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
090b0245dd59c458041ac16891614064a3e0d21d3464e2e844ffd25787c17f0b
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/BEFQERO5LHCFQBA2YFUJCYKAMS \
| 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: 090b0245dd59c458041ac16891614064a3e0d21d3464e2e844ffd25787c17f0b
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "68a69dbb823b02c186d7d5d111ff4d7260b7e85b049a205c70c05bac37fdfd7a",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.LG",
"submitted_at": "2025-09-30T16:17:21Z",
"title_canon_sha256": "5bc33420f94caab4993bbc8ef26ed4c8e36eec909e4e4de5786e73294215c2a3"
},
"schema_version": "1.0",
"source": {
"id": "2509.26469",
"kind": "arxiv",
"version": 4
}
}