Bayesian Program Learning by Decompiling Amortized Knowledge
DreamCoder is an inductive program synthesis system that, whilst solving problems, learns to simplify search in an iterative wake-sleep procedure. The cost of search is amortized by training a neural search policy, reducing search breadth and effectively "compiling" useful information to compose program solutions across tasks. Additionally, a library of program components is learnt to compress and express discovered solutions in fewer components, reducing search depth. We present a novel approach for library learning that directly leverages the neural search policy, effectively "decompiling" its amortized knowledge to extract relevant program components. This provides stronger amortized inference: the amortized knowledge learnt to reduce search breadth is now also used to reduce search depth. We integrate our approach with DreamCoder and demonstrate faster domain proficiency with improved generalization on a range of domains, particularly when fewer example solutions are available.
Code (0)
등록된 구현이 없습니다.
Tasks
Program inductionProgram SynthesisMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Deep Amortized Inference for Probabilistic Programs
Probabilistic programming languages (PPLs) are a powerful modeling tool, able to represent any computable probability distribution. Unfortunately, probabilistic program inference is often intractable, and existing PPLs m…
Probabilistic ProgrammingDetecting Model Misspecification in Amortized Bayesian Inference with Neural Networks
Neural density estimators have proven remarkably powerful in performing efficient simulation-based Bayesian inference in various research domains. In particular, the BayesFlow framework uses a two-step approach to enable…
Bayesian InferenceDecision Makingparameter estimationProbabilistic Deep LearningJANA: Jointly Amortized Neural Approximation of Complex Bayesian Models
This work proposes ``jointly amortized neural approximation'' (JANA) of intractable likelihood functions and posterior densities arising in Bayesian surrogate modeling and simulation-based inference. We train three compl…
DiagnosticTime SeriesTime Series AnalysisA Statistical Assessment of Amortized Inference Under Signal-to-Noise Variation and Distribution Shift
Since the turn of the century, approximate Bayesian inference has steadily evolved as new computational techniques have been incorporated to handle increasingly complex and large-scale predictive problems. The recent suc…
Bayesian InferenceBayesFlow: Amortized Bayesian Workflows With Neural Networks
Modern Bayesian inference involves a mixture of computational techniques for estimating, validating, and drawing conclusions from probabilistic models as part of principled workflows for data analysis. Typical problems i…
Bayesian InferenceData Compression