Unverified50% confidenceFactExact time
Near the loss minimum, the loss increase is approximately ΔL ≈ ½ · H · δ², where H is the curvature (second derivative) and δ is the quantization error range.
1
Sources
50%
Confidence
Long-term
Relevance
10/17/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedGradient descent updates parameters through the iterative formula θ = θ - α∇J(θ), where α is the learning rate and ∇J(θ) is the vector of partial derivatives of the loss function with respect to the parameters.76% similarUnverifiedWhen the quantile level τ=0.5, quantile loss degenerates to Mean Absolute Error (MAE).74% similarUnverifiedThe weight decay constant λ* introduced in the work is defined as λ* = 1 − αₗᵣ·λ, where αₗᵣ is the learning rate and λ is the original weight decay coefficient.73% similarUnverifiedThe gradient descent update rule is v → v − η∇C; since η > 0 and ‖∇C‖² ≥ 0, each update is guaranteed to decrease the cost, ΔC ≤ 0.72% similarUnverifiedRidge regression shrinks regression coefficients toward zero but does not set them to zero by adding an L2 regularization term to the loss function, whereas LASSO (L1 regularization) produces sparse solutions.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1053584API
curl https://kongchang.com/api/v1/knowledge/claims/1053584MCP
get_claim(id=1053584)