Unverified50% confidenceFactExact time
Stieltjes-Wigert polynomials carry a log-normal weight structure and a learnable q parameter.
1
Sources
50%
Confidence
Long-term
Relevance
10/4/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedApplying logit penalties to 'overthinking marker tokens' can improve the accuracy of Qwen models on mathematical reasoning tasks.59% similarUnverified魏尔斯特拉斯极值定理保证连续函数在紧集上必取最值58% similarUnverifiedQ-learning、DQN 等算法本质上都是在近似求解贝尔曼最优方程58% similarUnverified策略梯度定理证明梯度可表示为∇J(θ) = E[∇log π(a|s;θ) · Q^π(s,a)]，使用log-derivative trick将对概率分布的求导转化为对log概率的求导乘以采样值58% similarUnverifiedLogistic regression assumes that the log-odds is a linear combination of features, maps to probability space via the sigmoid function, and uses cross-entropy (log-likelihood) as the objective function.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/971802API
curl https://kongchang.com/api/v1/knowledge/claims/971802MCP
get_claim(id=971802)