Many common machine learning methods involve the geometric annealing path, a sequence of intermediate densities between two distributions of interest constructed using the geometric average. While alternatives such as the moment-averaging path have demonstrated performance gains in some settings, their practical applicability remains limited by exponential family endpoint assumptions and a lack of closed form energy function. In this work, we introduce $q$-paths, a family of paths which is derived from a generalized notion of the mean, includes the geometric and arithmetic mixtures as special cases, and admits a simple closed form involving the deformed logarithm function from nonextensive thermodynamics. Following previous analysis of the geometric path, we interpret our $q$-paths as corresponding to a $q$-exponential family of distributions, and provide a variational representation of intermediate densities as minimizing a mixture of $\alpha$-divergences to the endpoints. We show that small deviations away from the geometric path yield empirical gains for Bayesian inference using Sequential Monte Carlo and generative model evaluation using Annealed Importance Sampling.
翻译:许多常见的机器学习方法涉及几何肛交路径,这是使用几何平均值构建的两种利益分布之间的中间密度序列。虽然瞬间稳定路径等替代方法在某些环境中显示出了性能收益,但其实际适用性仍然受到指数式家庭端点假设的限制,而且缺乏封闭式能量功能。在这项工作中,我们引入了以q$为单位的路径组合,该路径系源自对平均值的普遍概念,包括作为特例的几何和算术混合物,并承认一种简单的封闭形式,涉及非远距热动力学的变形对数函数。在对几何路径进行先前的分析之后,我们把我们的美元路径解释为对应美元分布大家庭的超值,并提供了中间密度的变式表示,将美元正值的混合物最小化到终点。我们指出,从几何路径的微偏离小偏离,将使用序列背面的蒙特卡洛和利用安妮氏感应感应度的基因模型评估,为海湾的推论结果。