Metraipolis › archive › dc_c8f250b2ea77
$TCP_α$: Margin-Controlled Confidence estimation for reliable Music Information Retrieval — arXiv:2608.20326
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.20326
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T11:48:51.458Z
- SHA-256 of the archived text
2c097257d54b3799eb2501d8553038f7274b3170ae5e9a97366b86b976e5b450- Stable URL of this page
https://metraipolis.com/documento/dc_c8f250b2ea77
How to cite
$TCP_α$: Margin-Controlled Confidence estimation for reliable Music Information Retrieval — arXiv:2608.20326 — arXiv (en), https://arxiv.org/abs/2608.20326 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c8f250b2ea77 (Metraipolis archive dc_c8f250b2ea77, sha256 2c097257d54b3799eb2501d8553038f7274b3170ae5e9a97366b86b976e5b450)
BibTeX
@misc{dcc8f250b2ea77,
title = {$TCP_α$: Margin-Controlled Confidence estimation for reliable Music Information Retrieval — arXiv:2608.20326},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.20326},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c8f250b2ea77; sha256 2c097257d54b3799eb2501d8553038f7274b3170ae5e9a97366b86b976e5b450},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20326. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Deep neural networks are often overconfident, assigning high confidence even to incorrect predictions. Consequently, users lack a reliable signal for deciding when a prediction can be trusted. Post-hoc confidence estimation addresses this by training a lightweight auxiliary head over a frozen classifier. Existing targets, however, suffer from inherent ambiguity: they assign overlapping confidence values to correct and incorrect predictions, while errors near the decision boundary receive confidence scores indistinguishable from correct predictions. In this work, we propose $TCP_\alpha$, a novel confidence target that resolves these limitations by introducing a margin-controlled penalty for misclassified samples. We prove that $TCP_\alpha$ guarantees complete separation between the target values of correct and incorrect predictions, with a separation margin that is independent of the number of classes and increases monotonically with the penalty parameter. Since accurate classifiers naturally produce very few errors, learning these targets results in a severely imbalanced regression problem. We therefore present a systematic study of training strategies for learning under this imbalance and identify an effective training configuration through extensive ablation studies. We evaluate the proposed approach on rāga identification, investigate its robustness under domain shift, and further validate it on frame-wise ornamentation detection without modifying the selected configuration. Across all settings, $TCP_\alpha$ consistently outperforms existing confidence targets for failure prediction. Rejecting only the least-confident 8\% of predictions improves the base model's macro-F1 from 0.89 to 0.98, while fine-tuning the confidence head with only 5\% labeled samples from a new corpus effectively restores performance under domain shift. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-21 in cs.LG). Categorie arXiv: Audio and Speech Processing (eess.AS) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.20326 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T11:47:43.395Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).