Unverified50% confidenceFactExact time
As 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).
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedFor 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≥2.79% 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57% similarUnverifiedWhen α0=γ (the most benign case), KRR-RF is minimax optimal for all r∈(0,1].57% similarUnverifiedSelecting K models from N candidates is a combinatorial explosion problem; when N=20 and K=5, the number of combinations already exceeds 15,000.55% 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.55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1042112API
curl https://kongchang.com/api/v1/knowledge/claims/1042112MCP
get_claim(id=1042112)