paper-with-me

Papers

Bayesian Program Learning by Decompiling Amortized Knowledge

2023-06-13 · Alessandro B. Palmarini, Christopher G. Lucas, N. Siddharth

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.

📄 PDF Abstract BibTeX arXiv:2306.07856

Code (0)

등록된 구현이 없습니다.

Tasks

Program inductionProgram Synthesis

Methods 이 논문이 사용한 방법론

Library 설명 없음

Similar Papers 제목 키워드 기반

Deep Amortized Inference for Probabilistic Programs

2016-10-18 · Daniel Ritchie, Paul Horsfall, Noah D. Goodman

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 Programming

Detecting Model Misspecification in Amortized Bayesian Inference with Neural Networks

2021-12-16 · Marvin Schmitt, Paul-Christian Bürkner, Ullrich Köthe, Stefan T. Radev

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 Learning

JANA: Jointly Amortized Neural Approximation of Complex Bayesian Models

2023-02-17 · Stefan T. Radev, Marvin Schmitt, Valentin Pratz, Umberto Picchini 외

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 Analysis

A Statistical Assessment of Amortized Inference Under Signal-to-Noise Variation and Distribution Shift

2026-01-12 · Roy Shivam Ram Shreshtth, Arnab Hazra, Gourab Mukherjee arxiv

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 Inference

BayesFlow: Amortized Bayesian Workflows With Neural Networks

2023-06-28 · Stefan T Radev, Marvin Schmitt, Lukas Schumacher, Lasse Elsemüller 외

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