Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2601.21581 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914290114494464 |
|---|---|
| author | Blørstad, Morten Mostein, Herman Jangsett Blaser, Nello Parviainen, Pekka |
| author_facet | Blørstad, Morten Mostein, Herman Jangsett Blaser, Nello Parviainen, Pekka |
| contents | Deep learning models struggle with uncertainty estimation. Many approaches are either computationally infeasible or underestimate uncertainty. We investigate \textit{BatchEnsemble} as a general and scalable method for uncertainty estimation across both tabular and time series tasks. To extend BatchEnsemble to sequential modeling, we introduce GRUBE, a novel BatchEnsemble GRU cell. We compare the BatchEnsemble to Monte Carlo dropout and deep ensemble models. Our results show that BatchEnsemble matches the uncertainty estimation performance of deep ensembles, and clearly outperforms Monte Carlo dropout. GRUBE achieves similar or better performance in both prediction and uncertainty estimation. These findings show that BatchEnsemble and GRUBE achieve similar performance with fewer parameters and reduced training and inference time compared to traditional ensembles. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_21581 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Evaluating Prediction Uncertainty Estimates from BatchEnsemble Blørstad, Morten Mostein, Herman Jangsett Blaser, Nello Parviainen, Pekka Machine Learning Deep learning models struggle with uncertainty estimation. Many approaches are either computationally infeasible or underestimate uncertainty. We investigate \textit{BatchEnsemble} as a general and scalable method for uncertainty estimation across both tabular and time series tasks. To extend BatchEnsemble to sequential modeling, we introduce GRUBE, a novel BatchEnsemble GRU cell. We compare the BatchEnsemble to Monte Carlo dropout and deep ensemble models. Our results show that BatchEnsemble matches the uncertainty estimation performance of deep ensembles, and clearly outperforms Monte Carlo dropout. GRUBE achieves similar or better performance in both prediction and uncertainty estimation. These findings show that BatchEnsemble and GRUBE achieve similar performance with fewer parameters and reduced training and inference time compared to traditional ensembles. |
| title | Evaluating Prediction Uncertainty Estimates from BatchEnsemble |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2601.21581 |