.png){kind=icon}
返回
Wasserstein dropout
.png){kind=icon}
OA
AI
DOI：10.1007/s10994-022-06230-8.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Despite of its importance for safe machine learning, uncertainty quantification for neural networks is far from being solved. State-of-the-art approaches to estimate neural uncertainties are often hybrid, combining parametric models with explicit or implicit (dropout-based) ensembling. We take another pathway and propose a novel approach to uncertainty quantification for regression tasks, Wasserstein dropout, that is purely non-parametric. Technically, it captures aleatoric uncertainty by means of dropout-based sub-network distributions. This is accomplished by a new objective which minimizes the Wasserstein distance between the label distribution and the model distribution. An extensive empirical analysis shows that Wasserstein dropout outperforms state-of-the-art methods, on vanilla test data as well as under distributional shift in terms of producing more accurate and stable uncertainty estimates.
Keyword:
Safe machine learning
Regression neural networks
Uncertainty estimation
Aleatoric uncertainty
Dropout
Object detection
期刊
IF:
2.9
论文数:
2.7K
被引数:
3.4W
机构
引用论文
Nail fold capillaroscopy differs widely between systemic sclerosis and chronic graft vs host disease of the skin.png)
Rheumatology
OAAI
RheumatologyIF0
OAAI分享收藏分享收藏Anti-CD19 CAR-T therapy for EBV-negative posttransplantation lymphoproliferative disease—a single center case seriesEBV阴性的移植后淋巴增生性疾病的Anti-CD19 car-t治疗-单中心病例系列
PREAI
分享收藏Pressure-Based Bioassay Perceived by a Flexible Pressure Sensor with Synergistic Enhancement of the Photothermal Effect通过具有协同增强光热效应的柔性压力传感器感知的基于压力的生物测定
PREAI
分享收藏Energy-aware, load balanced routing schemes for sensor networksProceedings. Tenth International Conference on Parallel and Distributed Systems, 2004. ICPADS 2004.
Proceedings. Tenth International Conference on Parallel and Distributed Systems, 2004. ICPADS 2004.IF0
PREAI
分享收藏分享收藏
查看更多内容