Meta-Amortized Variational Inference and Learning

Abstract

Despite the recent success in probabilistic modeling and their applications, generative models trained using traditional inference techniques struggle to adapt to new distributions, even when the target distribution may be closely related to the ones seen during training. In this work, we present a doubly-amortized variational inference procedure as a way to address this challenge. By sharing computation across not only a set of query inputs, but also a set of different, related probabilistic models, we learn transferable latent representations that generalize across several related distributions. In particular, given a set of distributions over images, we find the learned representations to transfer to different data transformations. We empirically demonstrate the effectiveness of our method by introducing the MetaVAE, and show that it significantly outperforms baselines on downstream image classification tasks on MNIST (10-50%) and NORB (10-35%).

arXiv commentFirst 2 authors contributed equally

References in corpus (15)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• WaveNet: A Generative Model for Raw Audio
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Matching Networks for One Shot Learning
• Recasting Gradient-Based Meta-Learning as Hierarchical Bayes
• Towards a Neural Statistician
• Meta-Learning Update Rules for Unsupervised Representation Learning
• Amortized Inference Regularization
• Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions
• The Variational Homoencoder: Learning to learn high capacity generative models from few examples
• Attentive Neural Processes
• Reweighted Wake-Sleep
• Fast Adaptation in Generative Models with Generative Matching Networks

Cited by in corpus (5)

• VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning
• A Comprehensive Overview and Survey of Recent Advances in Meta-Learning
• Multi-task Batch Reinforcement Learning with Metric Learning
• A Simple Framework for Uncertainty in Contrastive Learning
• ADAVI: Automatic Dual Amortized Variational Inference Applied To Pyramidal Bayesian Models