Implicit Variational Conditional Sampling with Normalizing Flows

07/06/2021
by   Vincent Moens, et al.
10

We present a method for conditional sampling with normalizing flows when only part of an observation is available. We rely on the following fact: if the flow's domain can be partitioned in such a way that the flow restrictions to subdomains keep the bijectivity property, a lower bound to the conditioning variable log-probability can be derived. Simulation from the variational conditional flow then amends to solving an equality constraint. Our contribution is three-fold: a) we provide detailed insights on the choice of variational distributions; b) we propose how to partition the input space of the flow to preserve bijectivity property; c) we propose a set of methods to optimise the variational distribution in specific cases. Through extensive experiments, we show that our sampling method can be applied with success to invertible residual networks for inference and classification.

READ FULL TEXT

page 8

page 9

page 17

research
08/12/2020

Sampling using SU(N) gauge equivariant flows

We develop a flow-based sampling algorithm for SU(N) lattice gauge theor...
research
07/12/2023

Embracing the chaos: analysis and diagnosis of numerical instability in variational flows

In this paper, we investigate the impact of numerical instability on the...
research
08/17/2023

Conditional Sampling of Variational Autoencoders via Iterated Approximate Ancestral Sampling

Conditional sampling of variational autoencoders (VAEs) is needed in var...
research
02/09/2021

Automatic variational inference with cascading flows

The automation of probabilistic reasoning is one of the primary aims of ...
research
06/17/2020

Towards Recurrent Autoregressive Flow Models

Stochastic processes generated by non-stationary distributions are diffi...
research
04/28/2023

Flow Away your Differences: Conditional Normalizing Flows as an Improvement to Reweighting

We present an alternative to reweighting techniques for modifying distri...
research
05/16/2022

Ergodic variational flows

This work presents a new class of variational family – ergodic variation...

Please sign up or login with your details

Forgot password? Click here to reset