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 2202.09478cs.LGcs.AIstat.CO
收藏

在贝叶斯深度神经网络中实现1000+次蒙特卡罗迭代的图重新参数化

Graph Reparameterizations for Enabling 1000+ Monte Carlo Iterations in Bayesian Deep Neural Networks

University of Wisconsin Madison(威斯康星大学麦迪逊分校)

Jurijs Nazarovs, Ronak R. Mehta, Vishnu Suresh Lokhande, Vikas Singh

摘要:

深度模型中的不确定性估计在许多现实应用中至关重要,并受益于过去几年的发展。最近的证据表明,现有的解决方案依赖于简单的高斯公式可能是不够的。然而,转移到其他分布需要蒙特卡罗(MC)采样来估计诸如KL散度之类的量:随着输入数据和模型的维度的增长,它可能是昂贵的并且缩放性差。这与计算图的结构直接相关,计算图可以作为所需MC样本数量的函数线性增长。在这里,我们构建了一个框架来描述这些计算图,并确定概率家庭的图形大小可以是独立的或只有弱依赖于MC样本的数量。这些族直接对应于大类的分布。从经验上讲,我们可以为计算机视觉中使用的更大架构的MC近似运行更大数量的迭代,并在自信的准确性、训练稳定性、记忆和训练时间方面获得性能增益。

英文摘要:

Uncertainty estimation in deep models is essential in many real-world applications and has benefited from developments over the last several years. Recent evidence suggests that existing solutions dependent on simple Gaussian formulations may not be sufficient. However, moving to other distributions necessitates Monte Carlo (MC) sampling to estimate quantities such as the KL divergence: it could be expensive and scales poorly as the dimensions of both the input data and the model grow. This is directly related to the structure of the computation graph, which can grow linearly as a function of the number of MC samples needed. Here, we construct a framework to describe these computation graphs, and identify probability families where the graph size can be independent or only weakly dependent on the number of MC samples. These families correspond directly to large classes of distributions. Empirically, we can run a much larger number of iterations for MC approximations for larger architectures used in computer vision with gains in performance measured in confident accuracy, stability of training, memory and training time.

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。

↑