Metraipolis › archive › dc_3de0de3ff469

A Hierarchy of Entropy-Shapley Games for Multivariate Predictive Uncertainty — arXiv:2609.35217

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35217
License (as archived)
CC0-1.0
Archived
2026-10-07T22:41:09.250Z
SHA-256 of the archived text
e6e5d71b0b0dae4d76dc3f15f87d738d820443412f951fe44019bfa7b7fdf95d
Stable URL of this page
https://metraipolis.com/documento/dc_3de0de3ff469

How to cite

A Hierarchy of Entropy-Shapley Games for Multivariate Predictive Uncertainty — arXiv:2609.35217 — arXiv (en), https://arxiv.org/abs/2609.35217 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3de0de3ff469 (Metraipolis archive dc_3de0de3ff469, sha256 e6e5d71b0b0dae4d76dc3f15f87d738d820443412f951fe44019bfa7b7fdf95d)
BibTeX
@misc{dc3de0de3ff469,
  title = {A Hierarchy of Entropy-Shapley Games for Multivariate Predictive Uncertainty — arXiv:2609.35217},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35217},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3de0de3ff469; sha256 e6e5d71b0b0dae4d76dc3f15f87d738d820443412f951fe44019bfa7b7fdf95d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35217. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modern probabilistic machine learning models increasingly produce multivariate outputs with complex dependence structure, from multi-step time-series forecasts to sample path predictions. Understanding which input features drive the predictive uncertainty is important for risk-aware decisions, model diagnostics, and deciding whether the uncertainty should be mitigated or hedged against. This attribution problem requires a choice of how dependencies between output components are treated. Existing approaches reduce the output to a scalar through aggregation or projection before attribution, thereby obscuring whether features affect marginal uncertainty, dependence structure, or both, while component-wise analyses can miss dependence effects entirely. We close this gap by introducing a hierarchy of three entropy-based Shapley games that make this output-side choice explicit for any ordered multivariate outcome, ranging from per-component marginal entropy to fully joint entropy. The hierarchy isolates a cross-component attribution term that captures how each feature shifts the dependence between output components, a quantity invisible to component-wise methods. We establish a chain-rule decomposition of the joint attribution and characterize the cross-component term through conditional total correlation, providing both closed-form and sample-based estimators. Finally, we demonstrate how the framework captures differences in learned joint structure across probabilistic models from distributional regression to a zero-shot time series foundation model.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.35217 — 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 2026-10-07T22:14:28.912Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).