Mutual information (MI) is a fundamental quantity in information theory and machine learning. However, direct estimation of MI is intractable, even if the true joint probability density for the variables of interest is known, as it involves estimating a potentially high-dimensional log partition function. In this work, we present a unifying view of existing MI bounds from the perspective of importance sampling, and propose three novel bounds based on this approach. Since accurate estimation of MI without density information requires a sample size exponential in the true MI, we assume either a single marginal or the full joint density information is known. In settings where the full joint density is available, we propose Multi-Sample Annealed Importance Sampling (AIS) bounds on MI, which we demonstrate can tightly estimate large values of MI in our experiments. In settings where only a single marginal distribution is known, we propose Generalized IWAE (GIWAE) and MINE-AIS bounds. Our GIWAE bound unifies variational and contrastive bounds in a single framework that generalizes InfoNCE, IWAE, and Barber-Agakov bounds. Our MINE-AIS method improves upon existing energy-based methods such as MINE-DV and MINE-F by directly optimizing a tighter lower bound on MI. MINE-AIS uses MCMC sampling to estimate gradients for training and Multi-Sample AIS for evaluating the bound. Our methods are particularly suitable for evaluating MI in deep generative models, since explicit forms of the marginal or joint densities are often available. We evaluate our bounds on estimating the MI of VAEs and GANs trained on the MNIST and CIFAR datasets, and showcase significant gains over existing bounds in these challenging settings with high ground truth MI.
翻译:信息( MI) 是信息理论和机器学习的基本内容 。 然而, 直接估算 MI 是难以理解的, 即使已知了相关变量的真正共同概率密度, 因为它涉及估算潜在的高维日志分割功能。 在这项工作中, 我们从重要抽样的角度展示了对现有MI界限的统一观点, 并基于这一方法提出了三个新颖的界限。 由于准确估算MI没有密度信息需要在真正的MI中进行一个抽样规模指数指数化, 我们假设在具备完整联合密度的环境下, MI是一个单一的边际或完整的联合密度信息。 在具备完整联合密度的环境下, 我们建议多Sample Annaaled State States Saming( AIS) MIMI(A) 的界限, 我们可以在实验中严格估计MIMII( MIIS) 的数值值值。 在只知道单一边际分布的环境下, 我们建议将这些IWA( GIWAE) 和MIIS( MINA) 的直径直径评估方法( ), 在现有的IMIS( IMIS) 直接地( IMIS) ) 的常规方法上, 改进了我们现有 的常规数据,, 和不断升级的模型(, 的模型( ) ) 的模型( ) 的模型( ) 的模型( ) ) ) 的模型( ) ) 的模型( ) 的模型( ) ) ),,, 的模型( ) 直接评估方法可以直接地( ) 改进到, 的深度数据,,,,, 和 以现有 和 以现有 以现有 以现有 以现有 直径直径直径 方法改进 ) ) 方法为 方法为 的深度数据 直 的 的 的 方法改进 的深度数据,,, 直径。</s>