Unverified50% confidenceFactExact time
For Gaussian arms with a common variance, H₁-SR achieves at least 11/12 of the optimal normalized rate among all adaptive algorithms, and this ratio holds for any K≥2.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAs the number of candidate arms K tends to infinity, H₁-SR's approximation ratio converges to 1 at a rate of 1-O(1/log K).79% similarUnverifiedFor Gaussian arms with a common variance, SR's worst-case error exponent (after normalization by H₁(P)) is already optimal up to a constant factor.70% similarUnverifiedWhen α0=γ (the most benign case), KRR-RF is minimax optimal for all r∈(0,1].65% similarUnverified在MoE模型中每个token只激活少量Expert（通常2-4个，Top-K路由），实际计算量可能仅相当于6-7B的Dense模型63% similarUnverifiedThe K-Quants technique adopted by llama.cpp groups weights (typically 32 or 64 weights per group) and uses the K-means clustering algorithm on each group to find the optimal quantization codebook57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1042111API
curl https://kongchang.com/api/v1/knowledge/claims/1042111MCP
get_claim(id=1042111)