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 2302.02713cs.LGcs.ITmath.IT
收藏

平坦性寻求贝叶斯神经网络

Flat Seeking Bayesian Neural Networks

Monash University(莫纳什大学);VinAI(VinAI人工智能研究院);New York University(纽约大学)

Van-Anh Nguyen, Tung-Long Vuong, Hoang Phan, Thanh-Toan Do, Dinh Phung, Trung Le

AI总结:

本文提出锐度感知后验及其变分推断方法,使贝叶斯神经网络采样的模型具有更好平坦性,从而提升泛化能力,实验验证其优于基线。

摘要:

贝叶斯神经网络(BNNs)通过对模型参数施加先验分布,并基于观测数据推断后验分布,为深度学习模型提供了一种概率解释。从后验分布中采样的模型可用于提供集成预测和量化预测不确定性。众所周知,具有较低锐度(sharpness)的深度学习模型具有更好的泛化能力。然而,现有的后验推断在公式化方面并未考虑锐度/平坦性,这可能导致从中采样的模型具有较高的锐度。在本文中,我们为锐度感知后验(sharpness-aware posterior)发展了理论、贝叶斯设置和变分推断方法。具体而言,从我们的锐度感知后验中采样的模型,以及估计该锐度感知后验的最优近似后验,具有更好的平坦性,因此可能具有更高的泛化能力。我们通过将锐度感知后验与最先进的贝叶斯神经网络结合进行实验,结果表明,在所有感兴趣的指标上,寻求平坦性的对应模型均优于其基线模型。

英文摘要:

Bayesian Neural Networks (BNNs) provide a probabilistic interpretation for deep learning models by imposing a prior distribution over model parameters and inferring a posterior distribution based on observed data. The model sampled from the posterior distribution can be used for providing ensemble predictions and quantifying prediction uncertainty. It is well-known that deep learning models with lower sharpness have better generalization ability. However, existing posterior inferences are not aware of sharpness/flatness in terms of formulation, possibly leading to high sharpness for the models sampled from them. In this paper, we develop theories, the Bayesian setting, and the variational inference approach for the sharpness-aware posterior. Specifically, the models sampled from our sharpness-aware posterior, and the optimal approximate posterior estimating this sharpness-aware posterior, have better flatness, hence possibly possessing higher generalization ability. We conduct experiments by leveraging the sharpness-aware posterior with state-of-the-art Bayesian Neural Networks, showing that the flat-seeking counterparts outperform their baselines in all metrics of interest.

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。

↑