7 papers
SIDDA: SInkhorn Dynamic Domain Adaptation for Image Classification with Equivariant Neural Networks
Sneh Pandya, Purvik Patel, Brian D. Nord +2
Modern neural networks (NNs) often do not generalize well in the presence of a "covariate shift"; that is, in situations where the training and test data distributions differ, but…
On the Need to Align Intent and Implementation in Uncertainty Quantification for Machine Learning
Shubhendu Trivedi, Brian D. Nord
Quantifying uncertainties for machine learning (ML) models is a foundational challenge in modern data analysis. This challenge is compounded by at least two key aspects of the fiel…
Deep inference of simulated strong lenses in ground-based surveys
Jason Poh, Ashwin Samudre, Aleksandra ÄiprijanoviÄ +3
The large number of strong lenses discoverable in future astronomical surveys will likely enhance the value of strong gravitational lensing as a cosmic probe of dark energy and dar…
Symmetry-Based Structured Matrices for Efficient Approximately Equivariant Networks
Ashwin Samudre, Mircea Petrache, Brian D. Nord +1
There has been much recent interest in designing neural networks (NNs) with relaxed equivariance, which interpolate between exact equivariance and full flexibility for consistent p…
Neural Network Prediction of Strong Lensing Systems with Domain Adaptation and Uncertainty Quantification
Shrihan Agarwal, Aleksandra ÄiprijanoviÄ, Brian D. Nord
Modeling strong gravitational lenses is computationally expensive for the complex data from modern and next-generation cosmic surveys. Deep learning has emerged as a promising appr…
DeepUQ: Assessing the Aleatoric Uncertainties from two Deep Learning Methods
Rebecca Nevin, Aleksandra ÄiprijanoviÄ, Brian D. Nord
Assessing the quality of aleatoric uncertainty estimates from uncertainty quantification (UQ) deep learning methods is important in scientific contexts, where uncertainty is physic…