# Calibration Loss

**URL:** <https://discuss.bayesflow.org/t/calibration-loss/232>\
**Category:** General\
**Created:** [February 25, 2026, 2:11pm UTC](https://discuss.bayesflow.org/t/calibration-loss/232 "2026-02-25T14:11:26Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![matthias.kloft](https://yyz1.discourse-cdn.com/flex007/user_avatar/discuss.bayesflow.org/matthias.kloft/32/164_2.png) [@matthias.kloft](https://discuss.bayesflow.org/u/matthias.kloft)\
**Post date:** [February 25, 2026, 2:11pm UTC](https://discuss.bayesflow.org/t/calibration-loss/232/1 "2026-02-25T14:11:26Z")

</div>

Hello fellow Bayesians,

were/are there any attempts towards integrating a calibration loss, e.g., as proposed in [[2310.13402] Calibrating Neural Simulation-Based Inference with Differentiable Coverage Probability](https://arxiv.org/abs/2310.13402) , into Bayesflow? I am currently experimenting with this and wonder what the community’s take on this approach is.

Greetings, Matze

---

<div class="post-metadata">

**Author:** ![KLDivergence](https://yyz1.discourse-cdn.com/flex007/user_avatar/discuss.bayesflow.org/kldivergence/32/15_2.png) [@KLDivergence](https://discuss.bayesflow.org/u/KLDivergence)\
**Post date:** [March 2, 2026, 1:15pm UTC](https://discuss.bayesflow.org/t/calibration-loss/232/2 "2026-03-02T13:15:26Z")

</div>

Hi Matze, the feature is not planned yet but I would be happy to hear about your experience with the method outside the results in the paper.

---

<div class="post-metadata">

**Author:** ![matthias.kloft](https://yyz1.discourse-cdn.com/flex007/user_avatar/discuss.bayesflow.org/matthias.kloft/32/164_2.png) [@matthias.kloft](https://discuss.bayesflow.org/u/matthias.kloft)\
**Post date:** [March 3, 2026, 12:47pm UTC](https://discuss.bayesflow.org/t/calibration-loss/232/3 "2026-03-03T12:47:48Z")

</div>

I will post the repository here once I have a working proof of concept.