Learning to learn generative programs with Memoised Wake-Sleep

Abstract

We study a class of neuro-symbolic generative models in which neural networks are used both for inference and as priors over symbolic, data-generating programs. As generative models, these programs capture compositional structures in a naturally explainable form. To tackle the challenge of performing program induction as an 'inner-loop' to learning, we propose the Memoised Wake-Sleep (MWS) algorithm, which extends Wake Sleep by explicitly storing and reusing the best programs discovered by the inference network throughout training. We use MWS to learn accurate, explainable models in three challenging domains: stroke-based character modelling, cellular automata, and few-shot learning in a novel dataset of real-world string concepts.

References in corpus (10)

• Auto-Encoding Variational Bayes
• Categorical Reparameterization with Gumbel-Softmax
• Structure Discovery in Nonparametric Regression through Compositional Kernel Search
• Neural Variational Inference and Learning in Belief Networks
• REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models
• RobustFill: Neural Program Learning under Noisy I/O
• Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing
• Neural Program Synthesis with Priority Queue Training
• Revisiting Reweighted Wake-Sleep for Models with Stochastic Control Flow
• Deep Directed Generative Autoencoders