Diversity regularization in deep ensembles
Calibrating the confidence of supervised learning models is important for a variety of contexts where the certainty over predictions should be reliable. However, it has been reported that deep neural network models are often too poorly calibrated for achieving complex tasks requiring reliable uncertainty estimates in their prediction. In this work, we are proposing a strategy for training deep ensembles with a diversity function regularization, which improves the calibration property while maintaining a similar prediction accuracy.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityPredictionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Improving robustness and calibration in ensembles with diversity regularization
Calibration and uncertainty estimation are crucial topics in high-risk environments. We introduce a new diversity regularizer for classification tasks that uses out-of-distribution samples and increases the overall accur…
DiversityOut-of-Distribution DetectionPathologies of Predictive Diversity in Deep Ensembles
Classic results establish that encouraging predictive diversity improves performance in ensembles of low-capacity models, e.g. through bagging or boosting. Here we demonstrate that these intuitions do not apply to high-c…
DiversityDeep Ensembles with Hierarchical Diversity Pruning
Diverse deep ensembles hold the potential for improving accuracy and robustness of deep learning models. Both pairwise and non-pairwise ensemble diversity metrics have been proposed over the past two decades. However, it…
DiversityPromoting High Diversity Ensemble Learning with EnsembleBench
Ensemble learning is gaining renewed interests in recent years. This paper presents EnsembleBench, a holistic framework for evaluating and recommending high diversity and high accuracy ensembles. The design of EnsembleBe…
BenchmarkingDiversityEnsemble LearningVocal Bursts Intensity PredictionPreventing Value Function Collapse in Ensemble Q-Learning by Maximizing Representation Diversity
The first deep RL algorithm, DQN, was limited by the overestimation bias of the learned Q-function. Subsequent algorithms proposed techniques to reduce this problem, without fully eliminating it. Recently, the Maxmin and…
DiversityQ-Learning