Differentiable annealed importance sampling (DAIS), proposed by Geffner &
Domke (2021) and Zhang et al. (2021), allows optimizing, among others, over the
initial distribution of AIS. In this paper, we show that, in the limit of many
transitions, DAIS minimizes the symmetrized KL divergence (Jensen-Shannon
divergence) between the initial and target distribution. Thus, DAIS can be seen
as a form of variational inference (VI) in that its initial distribution is a
parametric fit to an intractable target distribution. We empirically evaluate
the usefulness of the initial distribution as a variational distribution on
synthetic and real-world data, observing that it often provides more accurate
uncertainty estimates than standard VI (optimizing the reverse KL divergence),
importance weighted VI, and Markovian score climbing (optimizing the forward KL
divergence).

DAIS 是一种可微分的持续退火重要性采样方法，它通过最小化初始和目标分布之间的对称 KL 散度来进行变分推断。通过实证评估其在合成和真实数据上作为变分分布的有用性，发现与标准 VI、重要性加权 VI 和马尔科夫分数爬升相比，它常常能提供更准确的不确定性估计。