ASTRANet combines a redshift-free spectral classifier, a 16-score anomaly detector, and conformal prediction to identify and calibrate uncertainty for out-of-taxonomy astronomical transients.
Why relu networks yield high-confidence predictions far away from the training data and how to mitigate the problem
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Classifiers used in the wild, in particular for safety-critical systems, should not only have good generalization properties but also should know when they don't know, in particular make low confidence predictions far away from the training data. We show that ReLU type neural networks which yield a piecewise linear classifier function fail in this regard as they produce almost always high confidence predictions far away from the training data. For bounded domains like images we propose a new robust optimization technique similar to adversarial training which enforces low confidence predictions far away from the training data. We show that this technique is surprisingly effective in reducing the confidence of predictions far away from the training data while maintaining high confidence predictions and test error on the original classification task compared to standard training.
citation-role summary
dataset 1
citation-polarity summary
years
2026 2verdicts
CONDITIONAL 2roles
dataset 1polarities
use dataset 1representative citing papers
COMPASS formalizes HPC configuration questions as ML tasks on traces, quantifies recommendation trustworthiness, and delivers 65.93% lower average job turnaround time plus 80.93% lower node usage versus prior methods in simulator tests.
citing papers explorer
-
Catching Disguised Transients with ASTRANet: Anomaly-Aware Spectroscopic Classification and Conformal Calibration
ASTRANet combines a redshift-free spectral classifier, a 16-score anomaly detector, and conformal prediction to identify and calibrate uncertainty for out-of-taxonomy astronomical transients.
-
COMPASS: A Unified Decision-Intelligence System for Navigating Performance Trade-off in HPC
COMPASS formalizes HPC configuration questions as ML tasks on traces, quantifies recommendation trustworthiness, and delivers 65.93% lower average job turnaround time plus 80.93% lower node usage versus prior methods in simulator tests.