Neighborhood Smoothing for Calibration
arXiv:2610.09020v1 Announce Type: new Abstract: Modern neural networks are often miscalibrated, with a tendency to overconfidence. Existing train-time calibration methods largely modify task losses or calibration penalties, leaving neighborhood structure in learned representations underexploited. W…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-10-08 04:00 · arXiv cs.LG
Neighborhood Smoothing for Calibration