Modern approaches for simulation-based inference rely upon deep learning surrogates to enable approximate inference with computer simulators. In practice, the estimated posteriors' computational faithfulness is, however, rarely guaranteed. For example, Hermans et al. (2021) show that current simulation-based inference algorithms can produce posteriors that are overconfident, hence risking false inferences. In this work, we introduce Balanced Neural Ratio Estimation (BNRE), a variation of the NRE algorithm designed to produce posterior approximations that tend to be more conservative, hence improving their reliability, while sharing the same Bayes optimal solution. We achieve this by enforcing a balancing condition that increases the quantified uncertainty in small simulation budget regimes while still converging to the exact posterior as the budget increases. We provide theoretical arguments showing that BNRE tends to produce posterior surrogates that are more conservative than NRE's. We evaluate BNRE on a wide variety of tasks and show that it produces conservative posterior surrogates on all tested benchmarks and simulation budgets. Finally, we emphasize that BNRE is straightforward to implement over NRE and does not introduce any computational overhead.
A 1/R Law for Kurtosis Contrast in Balanced Mixtures
Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS)(翻译神经影像与数据科学转化研究中心);Georgia State University(佐治亚州立大学);Georgia Institute of Technology(佐治亚理工学院);Emory University(埃默里大学);Department of Computer Science(计算机科学系);School of Electrical and Computer Engineering(电气与计算机工程学院)
Variational Inference and Bayesian CNNs for Uncertainty Estimation in Multi-Factorial Bone Age Prediction
Institute of Computer Graphics and Vision(计算机图形与视觉研究所);Graz University of Technology(格拉茨理工大学);School of Computer Science(计算机科学学院);University of Auckland(奥克兰大学)
Uncertainty Estimations by Softplus normalization in Bayesian Convolutional Neural Networks with Variational Inference
TU Kaiserslautern(凯泽斯劳滕工业大学);MindGarage;Imperial College London(帝国理工学院);NeuralSpace;Luleå University of Technology(吕勒奥理工大学)
我们介绍了一种新的不确定性估计贝叶斯卷积神经网络与变分推理的分类任务。通过在最后一层对Softplus函数的输出进行归一化,我们以连贯的方式估计任意和认知的不确定性。权重的后验概率分布由Bayes by Backprop推断。首先,我们展示了这种可靠的变分推理方法可以作为各种网络架构的基本构造。在监督学习设置(MNIST,CIFAR-10,CIFAR-100)的多个数据集上,这种变分推理方法在相同的体系结构中实现了与频率论推理相当的性能,而两个必要的,不确定性和正则化的度量自然地结合在一起。其次,我们研究了我们提出的任意性和认知不确定性的度量是如何推导出来的,并在上述数据集上进行了验证。
Inference, Prediction, and Entropy-Rate Estimation of Continuous-time, Discrete-event Processes
W. M. Keck Science Department of Pitzer, Scripps, and Claremont McKenna College(皮泽学院、斯克里普斯学院和克莱蒙特·麦肯纳学院W.M.凯克科学系);University of California at Davis(加州大学戴维斯分校)