mlsanityData to 7 Oct 2026

Learning to learn generative programs with Memoised Wake-Sleep

arXiv 2007.03132 ↗First posted 6 Jul 2020cs.AI cs.LGcited by 15

Not on the map. Why?

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.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 2; 2023: 8; 2024: 2; 2025: 0; 2026: 1.

15 papers.

Sort:

By area:

  1. 2022GFlowNets and variational inferencecited by 103
  2. 2023Training Chain-of-Thought via Latent-Variable Inferencecited by 46
  3. 2023GFlowNet-EM for learning compositional latent variable modelscited by 40
  4. 2023Compositional diversity in visual concept learningcited by 7
  5. 2023Delta-AI: Local objectives for amortized inference in sparse graphical modelscited by 7
  6. 2024Learning to Edit Visual Programs with Self-Supervisioncited by 7
  7. 2022Drawing out of Distribution with Neuro-Symbolic Generative Modelscited by 5
  8. 2023Learning of Generalizable and Interpretable Knowledge in Grid-Based Reinforcement Learning Environmentscited by 5
  9. 2023Generating Pragmatic Examples to Train Neural Program Synthesizerscited by 5
  10. 2021Learning Evolved Combinatorial Symbols with a Neuro-symbolic Generative Modelcited by 3
  11. 2021Hybrid Memoised Wake-Sleep: Approximate Inference at the Discrete-Continuous Interfacecited by 3
  12. 2026GIFT: Bootstrapping Image-to-CAD Program Synthesis via Geometric Feedbackcited by 3
3 more
  1. 2023Bayesian Program Learning by Decompiling Amortized Knowledgecited by 2
  2. 2024Learning to Infer Generative Template Programs for Visual Conceptscited by 2
  3. 2023Natural Evolution Strategies as a Black Box Estimator for Stochastic Variational Inferencecited by 0