arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.01085cs.LGstat.MEstat.ML
收藏

高维变分推理的挑战与机遇

Challenges and Opportunities in High-dimensional Variational Inference

Akash Kumar Dhaka, Alejandro Catalina, Manushi Welandawe, Michael Riis Andersen, Jonathan Huggins, Aki Vehtari

摘要:

目前的黑盒变分推理(BBVI)方法需要用户做出许多设计选择-如选择变分目标和近似家庭-但很少有原则性的指导如何做到这一点。我们开发了一个概念框架和一套实验工具来了解这些选择的影响,我们利用这些工具来提出最佳实践,以最大限度地提高后验近似精度。我们的方法是基于联合分布和变分近似之间的密度比的预渐近尾行为的研究,然后利用重要性采样文献的见解和工具。我们的框架和支持实验有助于区分BBVI方法的行为,近似低维与中到高维后验。在后一种情况下,我们表明,质量覆盖变分目标是难以优化,不提高精度,但灵活的变分家庭可以提高精度和有效性的重要性采样-在成本的额外的优化挑战。因此,对于中高维后验,我们建议使用(模式搜索)排他性KL发散,因为它是最容易优化的,并改进变分族或使用模型参数变换,使后验和最佳变分近似更相似。另一方面,在低维设置,我们表明,重尾变分家庭和质量覆盖发散是有效的,可以增加的机会,近似可以改善重要性采样。

英文摘要:

Current black-box variational inference (BBVI) methods require the user to make numerous design choices -- such as the selection of variational objective and approximating family -- yet there is little principled guidance on how to do so. We develop a conceptual framework and set of experimental tools to understand the effects of these choices, which we leverage to propose best practices for maximizing posterior approximation accuracy. Our approach is based on studying the pre-asymptotic tail behavior of the density ratios between the joint distribution and the variational approximation, then exploiting insights and tools from the importance sampling literature. Our framework and supporting experiments help to distinguish between the behavior of BBVI methods for approximating low-dimensional versus moderate-to-high-dimensional posteriors. In the latter case, we show that mass-covering variational objectives are difficult to optimize and do not improve accuracy, but flexible variational families can improve accuracy and the effectiveness of importance sampling -- at the cost of additional optimization challenges. Therefore, for moderate-to-high-dimensional posteriors we recommend using the (mode-seeking) exclusive KL divergence since it is the easiest to optimize, and improving the variational family or using model parameter transformations to make the posterior and optimal variational approximation more similar. On the other hand, in low-dimensional settings, we show that heavy-tailed variational families and mass-covering divergences are effective and can increase the chances that the approximation can be improved by importance sampling.

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。

↑