Variational Filtering for Bayesian Last Layers with an Independent Binary Probit Surrogate
arXiv:2610.16578v1 Announce Type: new Abstract: Modern deep classifiers trained by gradient descent need many passes over the data to become accurate, and even then are not always well calibrated; post-hoc temperature scaling corrects calibration after training but cannot influence training-time ac…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-14 04:00 · arXiv stat.ML
Variational Filtering for Bayesian Last Layers with an Independent Binary Probit Surrogate