Unverified50% confidenceFactExact time
The basic idea of the median-of-means (MoM) estimator is to divide the samples into several groups, compute the mean of each group, and then take the median of these means; it can achieve exponential concentration under only finite variance or even lower-order moment conditions.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe new result gives a one-sided exponential bound for the concentration of the sample mean under only a p-th moment condition.68% similarUnverified分层回测将股票按因子值分为若干组（通常5组或10组），观察各组超额收益是否呈现单调分布，比单一IC指标更直观揭示因子非线性特征68% similarUnverifiedAfter consensus ranking, all three top-ranked metrics came from the average clustering coefficient family: the median, standard deviation, and mean of the average clustering coefficient, respectively.68% similarUnverifiedChecking whether a benchmark is saturated requires looking at the overall distribution spread, not just the top score; if first and tenth place differ by only a hair, the leaderboard is saturated.68% similarUnverifiedAcross all three concept categories, the median number of same-class samples required for data saturation consistently falls between 7 and 11.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1046114API
curl https://kongchang.com/api/v1/knowledge/claims/1046114MCP
get_claim(id=1046114)