arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.12294stat.MLcs.LGcs.NE
收藏

生成模型的进化变分优化

Evolutionary Variational Optimization of Generative Models

University of Oldenburg(奥尔登堡大学);CERN(欧洲核子研究中心)

Jakob Drefs, Enrico Guiraud, Jörg Lücke

摘要:

我们结合了两种流行的优化方法来获得生成模型的学习算法:变分优化和进化算法。通过使用截断后验作为变分分布族,实现了具有离散潜伏期的生成模型的组合。截断后验的变分参数是潜状态的集合。通过将这些状态解释为个体的基因组,并使用变分下界来定义适应度,我们可以应用进化算法来实现变分循环。所使用的变分分布是非常灵活的,我们表明,进化算法可以有效地和高效地优化变分界。此外,变分循环是普遍适用的(“黑盒”),不需要分析推导。为了显示普遍适用性,我们将该方法应用于三种生成模型(我们使用噪声或贝叶斯网络,二进制稀疏编码和尖峰和板条稀疏编码)。为了证明新的变分方法的有效性和效率,我们使用标准的图像去噪和修复的竞争基准。这些基准允许对各种方法进行定量比较,包括概率方法,深度确定性和生成网络以及非局部图像处理方法。在“zero-shot”学习类别中(当仅使用损坏的图像进行训练时),我们观察到进化变分算法在许多基准设置中显着提高了最先进的水平。对于一个著名的修复基准,我们还观察到所有类别的算法的最先进的性能,虽然我们只对损坏的图像进行训练。在一般情况下,我们的调查突出的重要性,研究生成模型的优化方法,以实现性能的改善。

英文摘要:

We combine two popular optimization approaches to derive learning algorithms for generative models: variational optimization and evolutionary algorithms. The combination is realized for generative models with discrete latents by using truncated posteriors as the family of variational distributions. The variational parameters of truncated posteriors are sets of latent states. By interpreting these states as genomes of individuals and by using the variational lower bound to define a fitness, we can apply evolutionary algorithms to realize the variational loop. The used variational distributions are very flexible and we show that evolutionary algorithms can effectively and efficiently optimize the variational bound. Furthermore, the variational loop is generally applicable ("black box") with no analytical derivations required. To show general applicability, we apply the approach to three generative models (we use noisy-OR Bayes Nets, Binary Sparse Coding, and Spike-and-Slab Sparse Coding). To demonstrate effectiveness and efficiency of the novel variational approach, we use the standard competitive benchmarks of image denoising and inpainting. The benchmarks allow quantitative comparisons to a wide range of methods including probabilistic approaches, deep deterministic and generative networks, and non-local image processing methods. In the category of "zero-shot" learning (when only the corrupted image is used for training), we observed the evolutionary variational algorithm to significantly improve the state-of-the-art in many benchmark settings. For one well-known inpainting benchmark, we also observed state-of-the-art performance across all categories of algorithms although we only train on the corrupted image. In general, our investigations highlight the importance of research on optimization methods for generative models to achieve performance improvements.

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。

↑