q-Paths: Generalizing the Geometric Annealing Path using Power Means

by   Vaden Masrani, et al.

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 α-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.


page 1

page 2

page 3

page 4


Annealed Importance Sampling with q-Paths

Annealed importance sampling (AIS) is the gold standard for estimating p...

Rho-Tau Bregman Information and the Geometry of Annealing Paths

Markov Chain Monte Carlo methods for sampling from complex distributions...

Parallel Tempering on Optimized Paths

Parallel tempering (PT) is a class of Markov chain Monte Carlo algorithm...

Likelihood Ratio Exponential Families

The exponential family is well known in machine learning and statistical...

Cumulant-free closed-form formulas for some common (dis)similarities between densities of an exponential family

It is well-known that the Bhattacharyya, Hellinger, Kullback-Leibler, α-...

Bregman Power k-Means for Clustering Exponential Family Data

Recent progress in center-based clustering algorithms combats poor local...

Locking and Quacking: Stacking Bayesian model predictions by log-pooling and superposition

Combining predictions from different models is a central problem in Baye...

Code Repositories

Please sign up or login with your details

Forgot password? Click here to reset