MLmagnituudi
MLmagnituudi is a metric used in machine learning to quantify the magnitude of a model’s response to changes in its input. It serves as a measure of how sensitive a model’s predictions are to perturbations in the input space, focusing on the scale of the local gradient or Jacobian.
Definition and variants: For a differentiable model f: R^n -> R, the local MLmagnituudi at input x
Computation: If the model is differentiable, gradients are obtained via automatic differentiation. For non-differentiable models or
Applications: MLmagnituudi is used to audit robustness to input perturbations, compare sensitivity across architectures or training
Limitations: The value depends on the chosen input distribution and output scale, so cross-task comparisons require
Origin and status: The term has appeared in some experimental, non-standard discussions within the ML community