Geometric features from per-layer MLP update trajectories fed to a sparse linear probe outperform maximum softmax probability for uncertainty quantification under selective abstention, with gains up to 21 AURC points.
Journal of the Royal Statistical Society Series B: Statistical Methodology , volume=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
spBART extends BART by modeling low-dimensional covariates parametrically for interpretability and high-dimensional epigenetic predictors nonparametrically, with a CV-based variable selection procedure, achieving AUC 0.96 on multiple myeloma epigenetic data.
PerturbedVAE disentangles perturbation-specific signals from invariant gene expression structure to recover causal representations and improve out-of-distribution prediction in single-cell perturbation modeling.
Three-average primal-dual methods achieve accelerated rates for computable accuracy certificates in convex optimization.
citing papers explorer
-
Reading Calibrated Uncertainty from Language Model Trajectories
Geometric features from per-layer MLP update trajectories fed to a sparse linear probe outperform maximum softmax probability for uncertainty quantification under selective abstention, with gains up to 21 AURC points.
-
Semi-Parametric Bayesian Additive Regression Trees for Risk Prediction with High-Dimensional Epigenetic Signatures and Low-Dimensional Covariates
spBART extends BART by modeling low-dimensional covariates parametrically for interpretability and high-dimensional epigenetic predictors nonparametrically, with a CV-based variable selection procedure, achieving AUC 0.96 on multiple myeloma epigenetic data.
-
What Makes a Representation Good for Single-Cell Perturbation Prediction?
PerturbedVAE disentangles perturbation-specific signals from invariant gene expression structure to recover causal representations and improve out-of-distribution prediction in single-cell perturbation modeling.
-
Accuracy Certificates for Convex Optimization at Accelerated Rates via Primal-Dual Averaging
Three-average primal-dual methods achieve accelerated rates for computable accuracy certificates in convex optimization.