论文标题
简单有效的VAE培训和校准解码器
Simple and Effective VAE Training with Calibrated Decoders
论文作者
论文摘要
变性自动编码器（VAE）为建模复杂分布提供了一种有效而简单的方法。但是，训练VAE通常需要大量的超参数调整，以确定潜在变量保留的最佳信息量。我们研究了校准解码器的影响，这些解码器了解解码分布的不确定性，并可以自动确定该信息对VAE性能的影响。尽管已经提出了许多学习校准解码器的方法，但许多采用VAE的最近的论文依赖于启发式超参数和临时修改。我们对校准解码器进行了首次全面的比较分析，并为简单有效的VAE培训提供了建议。我们的分析涵盖了一系列图像和视频数据集以及几个单像和顺序VAE模型。我们进一步对常用的高斯解码器提出了一种简单但新颖的修改，该解码器可以通过分析计算预测方差。我们从经验上观察到，我们的方法不需要使用启发式修改。项目网站位于https://orybkin.github.io/sigma-vae/
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 https://orybkin.github.io/sigma-vae/
