Sub-network Laplace approximations always underestimate full-model predictive variance, and two new gradient-based and greedy selection rules provide theoretically grounded improvements.
Ortega, Simón Rodríguez Santana, and Daniel Hern’andez-Lobato
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Derives optimal low-rank subspace for Laplace approx in BNNs, provides scalable outperforming version, and new comparison metric.
VOLTA, consisting of a deep encoder with learnable prototypes plus cross-entropy and post-hoc temperature scaling, matches or exceeds ten UQ baselines in accuracy, achieves lower expected calibration error, and performs well on out-of-distribution detection across CIFAR, SVHN, and corruption shifts.
citing papers explorer
-
Optimality of Sub-network Laplace Approximations: New Results and Methods
Sub-network Laplace approximations always underestimate full-model predictive variance, and two new gradient-based and greedy selection rules provide theoretically grounded improvements.
-
Low Rank Based Subspace Inference for the Laplace Approximation of Bayesian Neural Networks
Derives optimal low-rank subspace for Laplace approx in BNNs, provides scalable outperforming version, and new comparison metric.
-
VOLTA: The Surprising Ineffectiveness of Auxiliary Losses for Calibrated Deep Learning
VOLTA, consisting of a deep encoder with learnable prototypes plus cross-entropy and post-hoc temperature scaling, matches or exceeds ten UQ baselines in accuracy, achieves lower expected calibration error, and performs well on out-of-distribution detection across CIFAR, SVHN, and corruption shifts.