Generalized Decision Focused Learning under Imprecise Uncertainty--Theoretical Study
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915206126370816 |
|---|---|
| author | Shariatmadar, Keivan Yorke-Smith, Neil Osman, Ahmad Cuzzolin, Fabio Hallez, Hans Moens, David |
| author_facet | Shariatmadar, Keivan Yorke-Smith, Neil Osman, Ahmad Cuzzolin, Fabio Hallez, Hans Moens, David |
| contents | Decision Focused Learning has emerged as a critical paradigm for integrating machine learning with downstream optimisation. Despite its promise, existing methodologies predominantly rely on probabilistic models and focus narrowly on task objectives, overlooking the nuanced challenges posed by epistemic uncertainty, non-probabilistic modelling approaches, and the integration of uncertainty into optimisation constraints. This paper bridges these gaps by introducing innovative frameworks: (i) a non-probabilistic lens for epistemic uncertainty representation, leveraging intervals (the least informative uncertainty model), Contamination (hybrid model), and probability boxes (the most informative uncertainty model); (ii) methodologies to incorporate uncertainty into constraints, expanding Decision-Focused Learning's utility in constrained environments; (iii) the adoption of Imprecise Decision Theory for ambiguity-rich decision-making contexts; and (iv) strategies for addressing sparse data challenges. Empirical evaluations on benchmark optimisation problems demonstrate the efficacy of these approaches in improving decision quality and robustness and dealing with said gaps. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_17984 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Generalized Decision Focused Learning under Imprecise Uncertainty--Theoretical Study Shariatmadar, Keivan Yorke-Smith, Neil Osman, Ahmad Cuzzolin, Fabio Hallez, Hans Moens, David Machine Learning Optimization and Control Probability 68T37 90C70 49N30 F.4; G.3 Decision Focused Learning has emerged as a critical paradigm for integrating machine learning with downstream optimisation. Despite its promise, existing methodologies predominantly rely on probabilistic models and focus narrowly on task objectives, overlooking the nuanced challenges posed by epistemic uncertainty, non-probabilistic modelling approaches, and the integration of uncertainty into optimisation constraints. This paper bridges these gaps by introducing innovative frameworks: (i) a non-probabilistic lens for epistemic uncertainty representation, leveraging intervals (the least informative uncertainty model), Contamination (hybrid model), and probability boxes (the most informative uncertainty model); (ii) methodologies to incorporate uncertainty into constraints, expanding Decision-Focused Learning's utility in constrained environments; (iii) the adoption of Imprecise Decision Theory for ambiguity-rich decision-making contexts; and (iv) strategies for addressing sparse data challenges. Empirical evaluations on benchmark optimisation problems demonstrate the efficacy of these approaches in improving decision quality and robustness and dealing with said gaps. |
| title | Generalized Decision Focused Learning under Imprecise Uncertainty--Theoretical Study |
| topic | Machine Learning Optimization and Control Probability 68T37 90C70 49N30 F.4; G.3 |
| url | https://arxiv.org/abs/2502.17984 |