论文标题
变异方差：简单，可靠，校准的异质噪声方差参数化
Variational Variance: Simple, Reliable, Calibrated Heteroscedastic Noise Variance Parameterization
论文作者
论文摘要
当从（随机）变量同时拟合神经网络映射到依赖性高斯变量的均值和方差时，已经观察到脆性优化对回归和VAE的模型可能性不利。以前的工作已经增强了优化和改善的可能性，但其他基本的后验预测检查（PPC）都失败了。在PPC框架下，我们提出了批评，以测试预测均值和方差校准以及预测分布生成合理数据的能力。我们发现，我们吸引人的简单解决方案，以处理异质方差的变化，足以使方差正常，以通过这些PPC。我们考虑了现有和新颖的先验的各种各样的范围，发现我们的方法保留或超过现有模型的可能性，同时显着改善了回归和VAE的参数校准和样品质量。
Brittle optimization has been observed to adversely impact model likelihoods for regression and VAEs when simultaneously fitting neural network mappings from a (random) variable onto the mean and variance of a dependent Gaussian variable. Previous works have bolstered optimization and improved likelihoods, but fail other basic posterior predictive checks (PPCs). Under the PPC framework, we propose critiques to test predictive mean and variance calibration and the predictive distribution's ability to generate sensible data. We find that our attractively simple solution, to treat heteroscedastic variance variationally, sufficiently regularizes variance to pass these PPCs. We consider a diverse gamut of existing and novel priors and find our methods preserve or outperform existing model likelihoods while significantly improving parameter calibration and sample quality for regression and VAEs.
