Particle Smoothing Variational Objectives

by   Antonio Khalil Moretti, et al.

A body of recent work has focused on constructing a variational family of filtered distributions using Sequential Monte Carlo (SMC). Inspired by this work, we introduce Particle Smoothing Variational Objectives (SVO), a novel backward simulation technique and smoothed approximate posterior defined through a subsampling process. SVO augments support of the proposal and boosts particle diversity. Recent literature argues that increasing the number of samples K to obtain tighter variational bounds may hurt the proposal learning, due to a signal-to-noise ratio (SNR) of gradient estimators decreasing at the rate O(1/√(K)). As a second contribution, we develop theoretical and empirical analysis of the SNR in filtering SMC, which motivates our choice of biased gradient estimators. We prove that introducing bias by dropping Categorical terms from the gradient estimate or using Gumbel-Softmax mitigates the adverse effect on the SNR. We apply SVO to three nonlinear latent dynamics tasks and provide statistics to rigorously quantify the predictions of filtered and smoothed objectives. SVO consistently outperforms filtered objectives when given fewer Monte Carlo samples on three nonlinear systems of increasing complexity.


page 1

page 2

page 3

page 4


Variational Marginal Particle Filters

Variational inference for state space models (SSMs) is known to be hard ...

On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes

We show that the gradient estimates used in training Deep Gaussian Proce...

Uphill Roads to Variational Tightness: Monotonicity and Monte Carlo Objectives

We revisit the theory of importance weighted variational inference (IWVI...

Tighter Variational Bounds are Not Necessarily Better. A Research Report on Implementation, Ablation Study, and Extensions

This report explains, implements and extends the works presented in "Tig...

Neural Particle Smoothing for Sampling from Conditional Sequence Models

We introduce neural particle smoothing, a sequential Monte Carlo method ...

Please sign up or login with your details

Forgot password? Click here to reset