Unverified60% confidenceFactExact time
Huber loss behaves as quadratic penalty when the error is small (consistent with MSE) and degrades to linear penalty when the error is large (consistent with MAE), making it more robust to outliers and commonly used in regression tasks.
2
Sources
60%
Confidence
Long-term
Relevance
7/19/2026
First Seen
Sources
梯度下降与反向传播详解：神经网络学习机制从零拆解
Related Claims
UnverifiedThe Huber loss function uses quadratic loss when the residual is small (equivalent to Gaussian likelihood) and switches to linear loss when the residual exceeds threshold δ (equivalent to Laplace likelihood).80% similarUnverifiedQuantile loss is more robust to outliers than MSE and can implicitly characterize the asymmetry of prediction errors.72% similarUnverifiedIn allow/block pipelines, the costs of the two types of errors are often severely asymmetric: a mistaken block may only be a loss in user experience, whereas a mistaken allow may cause a safety incident.66% similarUnverifiedTraining the student model with pixel-level loss functions (L1+MSE) caused the output images to appear gray and flat, resembling an average of all possible results—a classic failure mode of regression-based losses on generative tasks.66% similarUnverifiedThe previously dominant view held that velocity fields trained with mean squared error (MSE) systematically underestimate velocity magnitudes, and that velocity scaling is a correction for this error.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/558139API
curl https://kongchang.com/api/v1/knowledge/claims/558139MCP
get_claim(id=558139)