Gradient-Based Program Synthesis with Neurally Interpreted Languages

• URL: http://arxiv.org/abs/2604.18907v1
• Date: Mon, 20 Apr 2026 23:14:48 GMT
• Title: Gradient-Based Program Synthesis with Neurally Interpreted Languages
• Abstract summary: We develop an instance of a Latent Adaptation Network architecture named Neural Language Interpreter.<n>It learns its own discrete, symbolic-like programming language end-to-end.<n>Our results establish a new path toward models that combine compositionality of discrete languages with gradient-based end-to-end learning of neural networks.
• Score: 19.734602525162106
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A central challenge in program induction has long been the trade-off between symbolic and neural approaches. Symbolic methods offer compositional generalisation and data efficiency, yet their scalability is constrained by formalisms such as domain-specific languages (DSLs), which are labour-intensive to create and may not transfer to new domains. In contrast, neural networks flexibly learn from data but tend to generalise poorly in compositional and out-of-distribution settings. We bridge this divide with an instance of a Latent Adaptation Network architecture named Neural Language Interpreter (NLI), which learns its own discrete, symbolic-like programming language end-to-end. NLI autonomously discovers a vocabulary of primitive operations and uses a novel differentiable neural executor to interpret variable-length sequences of these primitives. This allows NLI to represent programs that are not bound to a constant number of computation steps, enabling it to solve more complex problems than those seen during training. To make these discrete, compositional program structures amenable to gradient-based optimisation, we employ the Gumbel-Softmax relaxation, enabling the entire model to be trained end-to-end. Crucially, this same differentiability enables powerful test-time adaptation. At inference, NLI's program inductor provides an initial program guess. This guess is then refined via gradient descent through the neural executor, enabling efficient search for the neural program that best explains the given data. We demonstrate that NLI outperforms in-context learning, test-time training, and continuous latent program networks on tasks that require combinatorial generalisation and rapid adaptation to unseen tasks. Our results establish a new path toward models that combine the compositionality of discrete languages with the gradient-based search and end-to-end learning of neural networks.

Related papers

• Principled Approaches for Extending Neural Architectures to Function Spaces for Operator Learning [78.88684753303794]
  Deep learning has predominantly advanced through applications in computer vision and natural language processing.<n>Neural operators are a principled way to generalize neural networks to mappings between function spaces.<n>This paper identifies and distills the key principles for constructing practical implementations of mappings between infinite-dimensional function spaces.
  arXiv  Detail & Related papers  (2025-06-12T17:59:31Z)
• NNTile: a machine learning framework capable of training extremely large GPT language models on a single node [83.9328245724548]
  NNTile is based on a StarPU library, which implements task-based parallelism and schedules all provided tasks onto all available processing units.<n>It means that a particular operation, necessary to train a large neural network, can be performed on any of the CPU cores or GPU devices.
  arXiv  Detail & Related papers  (2025-04-17T16:22:32Z)
• Training Neural Networks as Recognizers of Formal Languages [87.06906286950438]
  We train and evaluate neural networks directly as binary classifiers of strings.<n>We provide results on a variety of languages across the Chomsky hierarchy for three neural architectures.<n>Our contributions will facilitate theoretically sound empirical testing of language recognition claims in future work.
  arXiv  Detail & Related papers  (2024-11-11T16:33:25Z)
• Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagation [49.44309457870649]
  Layer-wise Feedback feedback (LFP) is a novel training principle for neural network-like predictors.<n>LFP decomposes a reward to individual neurons based on their respective contributions.<n>Our method then implements a greedy reinforcing approach helpful parts of the network and weakening harmful ones.
  arXiv  Detail & Related papers  (2023-08-23T10:48:28Z)
• Nondeterministic Stacks in Neural Networks [0.456877715768796]
  We develop a differentiable data structure that efficiently simulates a nondeterministic pushdown automaton. We show that this raises their formal recognition power to arbitrary context-free languages. We also show that an RNN augmented with a nondeterministic stack is capable of surprisingly powerful behavior.
  arXiv  Detail & Related papers  (2023-04-25T16:00:40Z)
• Parallel Neural Networks in Golang [0.0]
  This paper describes the design and implementation of parallel neural networks (PNNs) with the novel programming language Golang. Golang and its inherent parallelization support proved very well for parallel neural network simulation by considerable decreased processing times compared to sequential variants.
  arXiv  Detail & Related papers  (2023-04-19T11:56:36Z)
• Intelligence Processing Units Accelerate Neuromorphic Learning [52.952192990802345]
  Spiking neural networks (SNNs) have achieved orders of magnitude improvement in terms of energy consumption and latency. We present an IPU-optimized release of our custom SNN Python package, snnTorch.
  arXiv  Detail & Related papers  (2022-11-19T15:44:08Z)
• Dynamic Inference with Neural Interpreters [72.90231306252007]
  We present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules. inputs to the model are routed through a sequence of functions in a way that is end-to-end learned. We show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner.
  arXiv  Detail & Related papers  (2021-10-12T23:22:45Z)
• Sequence-to-Sequence Learning with Latent Neural Grammars [12.624691611049341]
  Sequence-to-sequence learning with neural networks has become the de facto standard for sequence prediction tasks. While flexible and performant, these models often require large datasets for training and can fail spectacularly on benchmarks designed to test for compositional generalization. This work explores an alternative, hierarchical approach to sequence-to-sequence learning with quasi-synchronous grammars.
  arXiv  Detail & Related papers  (2021-09-02T17:58:08Z)
• Beyond Graph Neural Networks with Lifted Relational Neural Networks [14.63152363481139]
  We demonstrate a declarative differentiable programming framework based on the language of Lifted Neural Networks. Small parameterized programs are used to encode learning. We show how this idea can be used for an efficient encoding of a diverse range of advanced neural networks.
  arXiv  Detail & Related papers  (2020-07-13T10:10:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.