# Learning to learn generative programs with Memoised Wake-Sleep

arXiv: https://arxiv.org/abs/2007.03132 · HTML: https://mlsanity.com/paper/2007.03132/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jul 2020.

## Built on by (most cited first, 15 of 15)

- [GFlowNets and variational inference](https://mlsanity.com/paper/2210.00580/) (2022)
- [Training Chain-of-Thought via Latent-Variable Inference](https://mlsanity.com/paper/2312.02179/) (2023)
- [GFlowNet-EM for learning compositional latent variable models](https://mlsanity.com/paper/2302.06576/) (2023)
- [Compositional diversity in visual concept learning](https://mlsanity.com/paper/2305.19374/) (2023)
- [Delta-AI: Local objectives for amortized inference in sparse graphical models](https://mlsanity.com/paper/2310.02423/) (2023)
- [Learning to Edit Visual Programs with Self-Supervision](https://mlsanity.com/paper/2406.02383/) (2024)
- [Drawing out of Distribution with Neuro-Symbolic Generative Models](https://mlsanity.com/paper/2206.01829/) (2022)
- [Learning of Generalizable and Interpretable Knowledge in Grid-Based Reinforcement Learning Environments](https://mlsanity.com/paper/2309.03651/) (2023)
- [Generating Pragmatic Examples to Train Neural Program Synthesizers](https://mlsanity.com/paper/2311.05740/) (2023)
- [Learning Evolved Combinatorial Symbols with a Neuro-symbolic Generative Model](https://mlsanity.com/paper/2104.08274/) (2021)
- [Hybrid Memoised Wake-Sleep: Approximate Inference at the Discrete-Continuous Interface](https://mlsanity.com/paper/2107.06393/) (2021)
- [GIFT: Bootstrapping Image-to-CAD Program Synthesis via Geometric Feedback](https://mlsanity.com/paper/2603.27448/) (2026)
- [Bayesian Program Learning by Decompiling Amortized Knowledge](https://mlsanity.com/paper/2306.07856/) (2023)
- [Learning to Infer Generative Template Programs for Visual Concepts](https://mlsanity.com/paper/2403.15476/) (2024)
- [Natural Evolution Strategies as a Black Box Estimator for Stochastic Variational Inference](https://mlsanity.com/paper/2308.08053/) (2023)

## Abstract (arXiv)

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.