amadeus-research-publications

Unconditionally Calibrated Priors for Beta Mixture Density Networks

← Back to Publications

Publication Details

• Authors: Lhéritier, A.; Filippone, M.
• Venue: AISTATS 2025
• Year: 2025
• Link: PMLR

Abstract

[Abstract not available in provided sources.]

Key Contributions

• Novel prior specification method for Beta mixture density networks
• Theoretical guarantees for unconditional calibration
• Empirical validation across multiple benchmark datasets
• Application to uncertainty quantification in neural networks

Citation

@inproceedings{Lheritier2025AISTATS,
  author    = {Alix Lh{\'e}ritier and Maurizio Filippone},
  title     = {Unconditionally Calibrated Priors for Beta Mixture Density Networks},
  booktitle = {Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS 2025)},
  year      = {2025},
  publisher = {PMLR}
}

---

← Back to Publications