paper-with-me

Papers

Diversity regularization in deep ensembles

2018-02-22 · Changjian Shui, Azadeh Sadat Mozafari, Jonathan Marek, Ihsen Hedhli, Christian Gagné

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.

📄 PDF Abstract BibTeX arXiv:1802.07881

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityPrediction

Methods 이 논문이 사용한 방법론

Deep Ensembles 설명 없음

Similar Papers 제목 키워드 기반

Improving robustness and calibration in ensembles with diversity regularization

2022-01-26 · Hendrik Alexander Mehrtens, Camila González, Anirban Mukhopadhyay

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 Detection

Pathologies of Predictive Diversity in Deep Ensembles

2023-02-01 · Taiga Abe, E. Kelly Buchanan, Geoff Pleiss, John P. Cunningham

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…

Diversity

Deep Ensembles with Hierarchical Diversity Pruning

2021-01-01 · Yanzhao Wu, Ling Liu

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…

Diversity

Promoting High Diversity Ensemble Learning with EnsembleBench

2020-10-20 · Yanzhao Wu, Ling Liu, Zhongwei Xie, Juhyun Bae 외

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 Prediction

Preventing Value Function Collapse in Ensemble Q-Learning by Maximizing Representation Diversity

2021-01-01 · Hassam Sheikh, Ladislau Boloni

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