Unverified50% confidenceFactExact time
The lower bound for the submodel also applies to general ensembles, matching the upper bound of buffered ERM (ignoring logarithmic factors) in the question-scarce regime and part of the intermediate regime.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn the special case of a uniform design, this study obtains matching upper and lower bounds for pointwise CATE estimation at interior points, but the result is limited to the low-nuisance-smoothness regime.73% similarUnverifiedMechanism one: when labeled questions are relatively scarce, the Q^{-1/2} term dominates the excess risk, generic buffered ERM is optimal, and the marginal benefit of increasing the number of generations N is limited.70% similarUnverifiedThe study establishes non-asymptotic bounds on the conditional score estimation error, i.e., bounds that hold for finite sample sizes69% similarUnverifiedMatching upper and lower bounds imply theoretical optimality: the upper bound is given by the risk analysis of a specific estimator, and the lower bound is constructed through minimax lower bound techniques such as Le Cam, Fano or Assouad.68% similarUnverifiedUsing the median rather than the mean is to avoid disturbance of the metric by long-tail samples and to better reflect the handling experience of typical issues.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1046169API
curl https://kongchang.com/api/v1/knowledge/claims/1046169MCP
get_claim(id=1046169)