Meta-Learning for Variational Inference

07/06/2020
by   Ruqi Zhang, et al.
19

Variational inference (VI) plays an essential role in approximate Bayesian inference due to its computational efficiency and broad applicability. Crucial to the performance of VI is the selection of the associated divergence measure, as VI approximates the intractable distribution by minimizing this divergence. In this paper we propose a meta-learning algorithm to learn the divergence metric suited for the task of interest, automating the design of VI methods. In addition, we learn the initialization of the variational parameters without additional cost when our method is deployed in the few-shot learning scenarios. We demonstrate our approach outperforms standard VI on Gaussian mixture distribution approximation, Bayesian neural network regression, image generation with variational autoencoders and recommender systems with a partial variational autoencoder.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/27/2019

Uncertainty in Model-Agnostic Meta-Learning using Variational Inference

We introduce a new, rigorously-formulated Bayesian meta-learning algorit...
research
12/22/2018

Bayesian Meta-network Architecture Learning

For deep neural networks, the particular structure often plays a vital r...
research
12/26/2019

Variational Metric Scaling for Metric-Based Meta-Learning

Metric-based meta-learning has attracted a lot of attention due to its e...
research
09/17/2019

Refined α-Divergence Variational Inference via Rejection Sampling

We present an approximate inference method, based on a synergistic combi...
research
02/26/2022

Variational Inference with Gaussian Mixture by Entropy Approximation

Variational inference is a technique for approximating intractable poste...
research
08/27/2020

Meta-Learning with Shared Amortized Variational Inference

We propose a novel amortized variational inference scheme for an empiric...
research
02/19/2018

Distribution Matching in Variational Inference

The difficulties in matching the latent posterior to the prior, balancin...

Please sign up or login with your details

Forgot password? Click here to reset