TPV measures first-order sensitivity of model outputs to parameter perturbations, unifies robustness analysis under one lens, proves train-to-test convergence in overparameterized limits, and enables label-free pruning and model selection applications.
To achieve this faithfully, training must be done in eval mode, i.e., modules like batch norm and dropout should not be active
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TPV: Parameter Perturbations Through the Lens of Test Prediction Variance
TPV measures first-order sensitivity of model outputs to parameter perturbations, unifies robustness analysis under one lens, proves train-to-test convergence in overparameterized limits, and enables label-free pruning and model selection applications.