mlsanityData to 7 Oct 2026

Differentiable Programs with Neural Libraries

arXiv 1611.02109 ↗First posted 7 Nov 2016cs.LGcited by 30

Not on the map. Why?

Abstract (arXiv)

We develop a framework for combining differentiable programming languages with neural networks. Using this framework we create end-to-end trainable systems that learn to write interpretable algorithms with perceptual components. We explore the benefits of inductive biases for strong generalization and modularity that come from the program-like structure of our models. In particular, modularity allows us to learn a library of (neural) functions which grows and improves as more tasks are solved. Empirically, we show that this leads to lifelong learning systems that transfer knowledge to new tasks more effectively than baselines.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 6; 2022: 9; 2023: 4; 2024: 4; 2025: 3; 2026: 3.

30 papers.

Sort:

By area:

  1. 2024NExT: Teaching Large Language Models to Reason about Code Executioncited by 60
  2. 2021Learning to Synthesize Programs as Interpretable and Generalizable Policiescited by 59
  3. 2022How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Compositioncited by 27
  4. 2024Limits of Deep Learning: Sequence Modeling through the Lens of Complexity Theorycited by 19
  5. 2022From Perception to Programs: Regularize, Overparameterize, and Amortizecited by 13
  6. 2022Static Prediction of Runtime Errors by Learning to Execute Programs with External Resource Descriptionscited by 11
  7. 2019From explanation to synthesis: Compositional program induction for learning from demonstrationcited by 9
  8. 2022Construction of Hierarchical Neural Architecture Search Spaces based on Context-free Grammarscited by 9
  9. 2024REFACTOR: Learning to Extract Theorems from Proofscited by 9
  10. 2023Hierarchical Neural Program Synthesiscited by 7
  11. 2023Deciphering Raw Data in Neuro-Symbolic Learning with Provable Guaranteescited by 6
  12. 2023Smoothing Methods for Automatic Differentiation Across Conditional Branchescited by 6
18 more
  1. 2021Robot Program Parameter Inference via Differentiable Shadow Program Inversioncited by 5
  2. 2024Differentiable Logic Programming for Distant Supervisioncited by 4
  3. 2021Deep Algorithmic Question Answering: Towards a Compositionally Hybrid AI for Algorithmic Reasoningcited by 2
  4. 2022Automated causal inference in application to randomized controlled clinical trialscited by 2
  5. 2022NESTER: An Adaptive Neurosymbolic Method for Causal Effect Estimationcited by 1
  6. 2025Compiling to linear neuronscited by 1
  7. 2026Neural Decision-Propagation for Answer Set Programmingcited by 1
  8. 2021Understanding in Artificial Intelligencecited by 0
  9. 2021Procedures as Programs: Hierarchical Control of Situated Agents through Natural Languagecited by 0
  10. 2021Synthesizing Machine Learning Programs with PAC Guarantees via Statistical Sketchingcited by 0
  11. 2022Differentiable Quantum Programming with Unbounded Loopscited by 0
  12. 2022A Short Survey of Systematic Generalizationcited by 0
  13. 2022Neural Feature-Adaptation for Symbolic Predictions Using Pre-Training and Semantic Losscited by 0
  14. 2023A differentiable programming framework for spin modelscited by 0
  15. 2025MetaLint: Easy-to-Hard Generalization for Code Lintingcited by 0
  16. 2025Compiling to recurrent neuronscited by 0
  17. 2026Neural-Symbolic Integration with Evolvable Policiescited by 0
  18. 2026Differentiate the Evaluator, Not the Program: An Efficient Runtime Representation for Neuro-Symbolic Learningcited by 0