For local minimizers of l2-regularized nonlinear least squares, the prediction gap around its expected value is bounded by a Fisher-information-like weighted norm, yielding pointwise confidence intervals that widen outside the training data.
Model-based reinforcement learning with value-targeted regression
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Pointwise confidence estimation in the non-linear $\ell^2$-regularized least squares
For local minimizers of l2-regularized nonlinear least squares, the prediction gap around its expected value is bounded by a Fisher-information-like weighted norm, yielding pointwise confidence intervals that widen outside the training data.