Bayesian E(3)-equivariant MLPs with joint energy-force NLL loss achieve competitive accuracy while enabling uncertainty-guided active learning, OOD detection, and calibration.
A simple baseline for bayesian uncertainty in deep learning
3 Pith papers cite this work, alongside 182 external citations. Polarity classification is still indexing.
3
Pith papers citing it
182
external citations · external index
fields
cs.LG 3verdicts
UNVERDICTED 3representative citing papers
Foundation models slightly outperform task-specific models on probabilistic electricity price forecasts but the gap narrows or reverses with extra features or few-shot adaptation, showing that efficiency often outweighs marginal accuracy gains.
Structured dropout improves confidence calibration in CNNs by promoting ensemble diversity, with empirical support on SVHN, CIFAR-10, CIFAR-100 and in Bayesian active learning.
citing papers explorer
-
Bayesian E(3)-Equivariant Interatomic Potential with Iterative Restratification of Many-body Message Passing
Bayesian E(3)-equivariant MLPs with joint energy-force NLL loss achieve competitive accuracy while enabling uncertainty-guided active learning, OOD detection, and calibration.
-
Assessing the Performance-Efficiency Trade-off of Foundation Models in Probabilistic Electricity Price Forecasting
Foundation models slightly outperform task-specific models on probabilistic electricity price forecasts but the gap narrows or reverses with extra features or few-shot adaptation, showing that efficiency often outweighs marginal accuracy gains.
-
Confidence Calibration for Convolutional Neural Networks Using Structured Dropout
Structured dropout improves confidence calibration in CNNs by promoting ensemble diversity, with empirical support on SVHN, CIFAR-10, CIFAR-100 and in Bayesian active learning.