pith:IBOON75N
Cost-Aware Learning
By accounting for different sampling costs, cost-aware stochastic gradient descent reaches target accuracy at lower total cost and reduces token usage by up to 30 percent in LLM policy optimization.
arxiv:2604.28020 v2 · 2026-04-30 · cs.LG
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{IBOON75NXU35CHZHNVCJSICENA}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Empirical results on 1.5B and 8B LLMs demonstrate that our approach reduces the tokens used in policy optimization by up to about 30% while matching or exceeding baseline accuracy.
The per-component sampling costs are known in advance and can be used to set sampling probabilities without introducing bias that harms convergence; this is stated implicitly in the cost-aware SGD derivation and the GRPO adaptation.
Cost-aware SGD achieves target error with lower total sampling cost than standard methods, and Cost-Aware GRPO reduces token usage by up to 30% in LLM reinforcement learning while matching baseline performance.
Receipt and verification
| First computed | 2026-06-01T02:03:42.199752Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
405ce6ffadbd37d11f276d449920446828560d01b951f46c8598b9f01d0b33aa
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/IBOON75NXU35CHZHNVCJSICENA \
| 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: 405ce6ffadbd37d11f276d449920446828560d01b951f46c8598b9f01d0b33aa
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "e203bea884ca6872e40e862b8e31299cd16b3707afb0f879b35534da2de819c6",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-04-30T15:39:09Z",
"title_canon_sha256": "ceb970895d645166143f06e611672c4dc852112665822d98373e8c5c76a46a20"
},
"schema_version": "1.0",
"source": {
"id": "2604.28020",
"kind": "arxiv",
"version": 2
}
}