Variational autoencoders (VAEs) provide an effective and simple method for
modeling complex distributions. However, training VAEs often requires
considerable hyperparameter tuning to determine the optimal amount of
information retained by the latent variable. We study the impact of calibrated
decoders, which learn the uncertainty of the decoding distribution and can
determine this amount of information automatically, on the VAE performance.
While many methods for learning calibrated decoders have been proposed, many of
the recent papers that employ VAEs rely on heuristic hyperparameters and ad-hoc
modifications instead. We perform the first comprehensive comparative analysis
of calibrated decoder and provide recommendations for simple and effective VAE
training. Our analysis covers a range of image and video datasets and several
single-image and sequential VAE models. We further propose a simple but novel
modification to the commonly used Gaussian decoder, which computes the
prediction variance analytically. We observe empirically that using heuristic
modifications is not necessary with our method. Project website is at
this https URL

本文针对 VAE 模型中的超参数调整问题，研究了校准解码器的作用和对 VAE 性能的影响，提出了一种简单但有效的高斯解码器改进方法。通过对多种数据集和模型的综合分析，我们得出了使用校准解码器进行 VAE 训练的建议。

使用校准解码器进行简单有效的 VAE 训练

Simple and Effective VAE Training with Calibrated Decoders

We propose Learned Accept/Reject Sampling (LARS), a method for constructing
richer priors using rejection sampling with a learned acceptance function. This
work is motivated by recent analyses of the VAE objective, which pointed out
that commonly used simple priors can lead to underfitting. As the distribution
induced by LARS involves an intractable normalizing constant, we show how to
estimate it and its gradients efficiently. We demonstrate that LARS priors
improve VAE performance on several standard datasets both when they are learned
jointly with the rest of the model and when they are fitted to a pretrained
model. Finally, we show that LARS can be combined with existing methods for
defining flexible priors for an additional boost in performance.

提出了基于学习接受 / 拒绝采样的 LARS 方法，该方法可以使用具有学习接受函数的拒绝采样构建更丰富的先验，从而改善了变分自编码器（VAE）的性能，并且还可以与现有的灵活先验定义方法相结合以进一步提高性能。