Unverified50% confidenceFactExact time
For 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.
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≥2.70% similarUnverifiedWhen α0=γ (the most benign case), KRR-RF is minimax optimal for all r∈(0,1].67% similarUnverifiedMRR (Mean Reciprocal Rank) is more sensitive to top-ranked results, with a correct tool ranked 1st scoring 1 point, 2nd scoring 0.5 points, and 5th scoring 0.2 points.63% similarUnverifiedAfter re-evaluating with non-overlapping anchors, the net advantage instead grew from +4.1pp to +5.5pp, but significance dropped from 2.4 standard errors to 1.4 standard errors; the inflation factor is about 2.4x, exactly equal to sqrt(912/163).63% similarUnverifiedIn practice, r=8 or 16 offers the best cost-effectiveness for rank r, with typical values ranging from 4 to 64.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1042108API
curl https://kongchang.com/api/v1/knowledge/claims/1042108MCP
get_claim(id=1042108)