Unverified50% confidenceFactExact time
Quantile regression was first proposed by Koenker and Bassett, and its loss function is called the pinball loss.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedKaplan et al. found that the relationship between model loss and parameter count N approximately satisfies the power-law relationship L(N) ∝ N^(-0.076).62% similarUnverifiedQuantile regression was proposed by Koenker and Bassett in 1978.60% similarUnverifiedProspect theory, jointly proposed by Kahneman and Tversky, reveals that people's sensitivity to losses is approximately twice their sensitivity to equivalent gains.55% similarUnverifiedRate-distortion theory, proposed by Claude Shannon, studies the minimum level to which data can be compressed given a specified distortion tolerance.54% similarUnverifiedThe double descent phenomenon was systematically revealed by Belkin et al. in 2019, overturning the classical U-shaped test error curve.53% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1042090API
curl https://kongchang.com/api/v1/knowledge/claims/1042090MCP
get_claim(id=1042090)