pith:2JDHXKAY
Neural Variance-aware Dueling Bandits with Deep Representation and Shallow Exploration
Variance-aware neural algorithms for contextual dueling bandits achieve sublinear regret of order O(d sqrt(sum sigma_t^2) + sqrt(dT)).
arxiv:2506.01250 v3 · 2025-06-02 · cs.LG · stat.ML
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{2JDHXKAYJWQLMV6FJSH2M5ZAKT}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Under standard assumptions, our algorithms achieve sublinear cumulative average regret of order O(d sqrt(sum_{t=1}^T sigma_t^2) + sqrt(d T)) for sufficiently wide neural networks.
The neural networks must be sufficiently wide to approximate the unknown nonlinear utility functions, and the variance-aware exploration strategy must be effective when computed solely from last-layer gradients without requiring deeper network information.
Variance-aware neural dueling bandit algorithms achieve sublinear regret of order O(d sqrt(sum sigma_t^2) + sqrt(d T)) for wide networks on nonlinear utilities.
Receipt and verification
| First computed | 2026-06-04T01:08:29.442894Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
d2467ba8184da0b657c54c8fa6772054fcb519793c13ac6467754da944458d2e
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/2JDHXKAYJWQLMV6FJSH2M5ZAKT \
| 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: d2467ba8184da0b657c54c8fa6772054fcb519793c13ac6467754da944458d2e
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "a76a6ed15663fd9eb988b996d144c570cd05051e98f49335d6d8b3ae698d1228",
"cross_cats_sorted": [
"stat.ML"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.LG",
"submitted_at": "2025-06-02T01:58:48Z",
"title_canon_sha256": "935f4f67589a8b5afdac16c0e2762295ed0c7f3cc925a66e226d536209e36e6c"
},
"schema_version": "1.0",
"source": {
"id": "2506.01250",
"kind": "arxiv",
"version": 3
}
}