Saved in:
Bibliographic Details
Main Author: Hedges, C. Evans
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.04487
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918148560650240
author Hedges, C. Evans
author_facet Hedges, C. Evans
contents We study $\perp$Grad, a geometry-aware modification to gradient-based optimization that constrains descent directions to address overconfidence, a key limitation of standard optimizers in uncertainty-critical applications. By enforcing orthogonality between gradient updates and weight vectors, $\perp$Grad alters optimization trajectories without architectural changes. On CIFAR-10 with 10% labeled data, $\perp$Grad matches SGD in accuracy while achieving statistically significant improvements in test loss ($p=0.05$), predictive entropy ($p=0.001$), and confidence measures. These effects show consistent trends across corruption levels and architectures. $\perp$Grad is optimizer-agnostic, incurs minimal overhead, and remains compatible with post-hoc calibration techniques. Theoretically, we characterize convergence and stationary points for a simplified $\perp$Grad variant, revealing that orthogonalization constrains loss reduction pathways to avoid confidence inflation and encourage decision-boundary improvements. Our findings suggest that geometric interventions in optimization can improve predictive uncertainty estimates at low computational cost.
format Preprint
id arxiv_https___arxiv_org_abs_2506_04487
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OrthoGrad Improves Neural Calibration
Hedges, C. Evans
Machine Learning
We study $\perp$Grad, a geometry-aware modification to gradient-based optimization that constrains descent directions to address overconfidence, a key limitation of standard optimizers in uncertainty-critical applications. By enforcing orthogonality between gradient updates and weight vectors, $\perp$Grad alters optimization trajectories without architectural changes. On CIFAR-10 with 10% labeled data, $\perp$Grad matches SGD in accuracy while achieving statistically significant improvements in test loss ($p=0.05$), predictive entropy ($p=0.001$), and confidence measures. These effects show consistent trends across corruption levels and architectures. $\perp$Grad is optimizer-agnostic, incurs minimal overhead, and remains compatible with post-hoc calibration techniques. Theoretically, we characterize convergence and stationary points for a simplified $\perp$Grad variant, revealing that orthogonalization constrains loss reduction pathways to avoid confidence inflation and encourage decision-boundary improvements. Our findings suggest that geometric interventions in optimization can improve predictive uncertainty estimates at low computational cost.
title OrthoGrad Improves Neural Calibration
topic Machine Learning
url https://arxiv.org/abs/2506.04487