5 papers
Ribbon: Scalable Approximation and Robust Uncertainty Quantification
Graham Gibson, John Tipton, Kellin Rumsey +1
Reliably quantifying predictive uncertainty is difficult for complex, high-dimensional, or misspecified models. Both fully Bayesian and bootstrap resampling methods provide princip…
Effects of Structural Allocation of Geometric Task Diversity in Linear Meta-Learning Models
Saptati Datta, Nicolas W. Hengartner, Yulia Pimonova +2
Meta-learning aims to leverage information across related tasks to improve prediction on unlabeled data for new tasks when only a small number of labeled observations are available…
Meta-learning to Address Data Shift in Time Series Classification
Samuel Myren, Nidhi Parikh, Natalie Klein
Across engineering and scientific domains, traditional deep learning (TDL) models perform well when training and test data share the same distribution. However, the dynamic nature…
The Sensitivity of Variational Bayesian Neural Network Performance to Hyperparameters
Scott Koermer, Natalie Klein
In scientific applications, predictive modeling is often of limited use without accurate uncertainty quantification (UQ) to indicate when a model may be extrapolating or when more…
Regularization via f-Divergence: An Application to Multi-Oxide Spectroscopic Analysis
Weizhi Li, Natalie Klein, Brendan Gifford +3
In this paper, we address the task of characterizing the chemical composition of planetary surfaces using convolutional neural networks (CNNs). Specifically, we seek to predict the…