arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2008.03209cs.LGcs.AIstat.ML
收藏

基于最大似然的无限混合训练方法在不确定度量化中的应用研究

Investigating maximum likelihood based training of infinite mixtures for uncertainty quantification

Ruhr University Bochum(波鸿鲁尔大学)

Sina Däubener, Asja Fischer

摘要:

神经网络中的不确定性量化在过去几年中得到了很多关注。最流行的方法,贝叶斯神经网络(BNN),蒙特卡罗丢弃和深度集成有一个共同点:它们都基于某种混合模型。虽然BNN构建无限混合模型并通过变分推理推导,但后两者构建使用最大似然法训练的有限混合模型。在这项工作中,我们研究的效果训练的无限混合分布的最大似然方法,而不是变分推理。我们发现,所提出的目标导致随机网络的预测方差增加,这提高了基于不确定性的识别误分类和鲁棒性对对抗攻击相比,一个标准的BNN与等效的网络结构。新模型还在分布外数据上显示出更高的熵。

英文摘要:

Uncertainty quantification in neural networks gained a lot of attention in the past years. The most popular approaches, Bayesian neural networks (BNNs), Monte Carlo dropout, and deep ensembles have one thing in common: they are all based on some kind of mixture model. While the BNNs build infinite mixture models and are derived via variational inference, the latter two build finite mixtures trained with the maximum likelihood method. In this work we investigate the effect of training an infinite mixture distribution with the maximum likelihood method instead of variational inference. We find that the proposed objective leads to stochastic networks with an increased predictive variance, which improves uncertainty based identification of miss-classification and robustness against adversarial attacks in comparison to a standard BNN with equivalent network structure. The new model also displays higher entropy on out-of-distribution data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑