Diversity-Aware Agnostic Ensemble of Sharpness Minimizers
arxiv(2024)
摘要
There has long been plenty of theoretical and empirical evidence supporting
the success of ensemble learning. Deep ensembles in particular take advantage
of training randomness and expressivity of individual neural networks to gain
prediction diversity, ultimately leading to better generalization, robustness
and uncertainty estimation. In respect of generalization, it is found that
pursuing wider local minima result in models being more robust to shifts
between training and testing sets. A natural research question arises out of
these two approaches as to whether a boost in generalization ability can be
achieved if ensemble learning and loss sharpness minimization are integrated.
Our work investigates this connection and proposes DASH - a learning algorithm
that promotes diversity and flatness within deep ensembles. More concretely,
DASH encourages base learners to move divergently towards low-loss regions of
minimal sharpness. We provide a theoretical backbone for our method along with
extensive empirical evidence demonstrating an improvement in ensemble
generalizability.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要