Verified claim · AI-ML · 100% confidence
AdamW optimizer introduced in paper: Decoupled Weight Decay Regularization (Loshchilov & Hutter, 2017).
Last verified 2026-05-16 · Methodology veritas-v0.1 · b6d51eba4fc7f918
SourceScore rates how reliable a source is to cite — for AI answers and research. This is one verified claim from the catalog.
Structured fields
- Subject
- AdamW optimizer
- Predicate
introduced_in_paper- Object
- Decoupled Weight Decay Regularization (Loshchilov & Hutter, 2017)
- Confidence
- 100%
- Tags
- adamw · optimizer · weight-decay · foundational · 2017 · iclr
Sources (2)
[1] preprint · arXiv (Loshchilov, Hutter) · 2017-11-14
Decoupled Weight Decay Regularization“We propose a simple modification to recover the original formulation of weight decay regularization by decoupling the weight decay from the optimization steps taken w.r.t. the loss function.”
[2] peer reviewed · OpenReview / ICLR · 2019-05-06
Decoupled Weight Decay Regularization (ICLR 2019)
Cite this claim
Ready-to-paste citation (Markdown / plain text):
AdamW optimizer introduced in paper: Decoupled Weight Decay Regularization (Loshchilov & Hutter, 2017). — SourceScore Claim b6d51eba4fc7f918 (verified 2026-05-16). https://sourcescore.org/api/v1/claims/b6d51eba4fc7f918.jsonEmbed this claim
Drop this iframe into any blog post, docs page, or knowledge base. The widget renders the signed claim + primary source + click-through to this canonical page. CC-BY 4.0; attribution included.
<iframe src="https://sourcescore.org/embed/claim/b6d51eba4fc7f918/" width="100%" height="360" frameborder="0" loading="lazy" title="AdamW optimizer introduced in paper: Decoupled Weight Decay Regularization (Loshchilov & Hutter, 2017)."></iframe>Preview: open in new tab
Related claims
Other verified claims sharing tags with this one — useful for LLM retrieval graphs and citation discovery.
Adam optimizer introduced in paper: Adam: A Method for Stochastic Optimization (Kingma, Ba, 2014).
dffbe905003cc581 · 100% confidence · shares 3 tags (optimizer, foundational, iclr)
Mixture of Experts (MoE) revival popularized in: Shazeer et al. 2017 — outrageously large neural networks via sparse gating.
f068236101568ad7 · 100% confidence · shares 3 tags (foundational, iclr, 2017)
Transformer architecture introduced in paper: Attention Is All You Need (Vaswani et al., 2017).
ad17e76a8baad7a1 · 100% confidence · shares 2 tags (foundational, 2017)
Reinforcement Learning from Human Feedback (RLHF) introduced in paper: Deep Reinforcement Learning from Human Preferences (Christiano et al., 2017).
67866330cd60e54d · 100% confidence · shares 2 tags (foundational, 2017)
Sparsely-Gated Mixture-of-Experts (MoE) introduced in paper: Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer (Shazeer et al., 2017).
2d6d7f61f1db6493 · 100% confidence · shares 2 tags (foundational, 2017)
Frequently asked questions
Is the claim "AdamW optimizer introduced in paper: Decoupled Weight Decay Regularization (Loshchilov & Hutter, 2017)." verified?
Yes — SourceScore verified this claim with 100% confidence as of 2026-05-16. The verification uses 2 primary sources cross-referenced against the SourceScore methodology (version veritas-v0.1). Full source list + signed JSON envelope linked below.
What is the evidence for "AdamW optimizer introduced in paper: Decoupled Weight Decay Regularization (Loshchilov & Hutter, 2017)."?
Evidence comes from 2 primary sources: arXiv (Loshchilov, Hutter), OpenReview / ICLR. Each source is listed below with verbatim excerpts and URLs. The signed JSON envelope at https://sourcescore.org/api/v1/claims/b6d51eba4fc7f918.json includes an HMAC-SHA256 signature for audit verification.
When was this claim last verified by SourceScore?
Last verified 2026-05-16 under methodology version veritas-v0.1. The signed JSON envelope is dated and cryptographically signed for audit trail. Re-verification cadence depends on the claim type and source freshness.
How can I cite this SourceScore claim in my code or article?
Fetch the signed JSON envelope from https://sourcescore.org/api/v1/claims/b6d51eba4fc7f918.json which includes the verbatim claim, primary sources, confidence, methodology version, last-verified date, and HMAC-SHA256 signature for audit. The CC-BY-4.0 license permits commercial use with attribution to SourceScore.
Use this claim in your code
Fetch this signed envelope from your application. The response includes the verbatim excerpt, primary source URLs, and an HMAC-SHA256 signature you can verify locally for audit trails.
cURL
curl https://sourcescore.org/api/v1/claims/b6d51eba4fc7f918.jsonJavaScript / TypeScript
const r = await fetch("https://sourcescore.org/api/v1/claims/b6d51eba4fc7f918.json");
const envelope = await r.json();
console.log(envelope.claim.statement);
// "AdamW optimizer introduced in paper: Decoupled Weight Decay Regularization (Loshchilov & Hutter, 2017)."Python
import httpx
r = httpx.get("https://sourcescore.org/api/v1/claims/b6d51eba4fc7f918.json")
envelope = r.json()
print(envelope["claim"]["statement"])
# "AdamW optimizer introduced in paper: Decoupled Weight Decay Regularization (Loshchilov & Hutter, 2017)."LangChain (retrieve-then-cite)
from langchain_core.tools import tool
import httpx
@tool
def get_adamw_optimizer_fact() -> dict:
"""Fetch the verified SourceScore claim for AdamW optimizer."""
r = httpx.get("https://sourcescore.org/api/v1/claims/b6d51eba4fc7f918.json")
return r.json()