paper-with-me

Papers

Towards Efficient Neurally-Guided Program Induction for ARC-AGI

2024-11-13 · Simon Ouellette

ARC-AGI is an open-world problem domain in which the ability to generalize out-of-distribution is a crucial quality. Under the program induction paradigm, we present a series of experiments that reveal the efficiency and generalization characteristics of various neurally-guided program induction approaches. The three paradigms we consider are Learning the grid space, Learning the program space, and Learning the transform space. We implement and experiment thoroughly on the first two, and retain the second one for ARC-AGI submission. After identifying the strengths and weaknesses of both of these approaches, we suggest the third as a potential solution, and run preliminary experiments.

📄 PDF Abstract BibTeX arXiv:2411.17708

Code (0)

등록된 구현이 없습니다.

Tasks

ARCProgram induction

Similar Papers 제목 키워드 기반

Library Learning for Neurally-Guided Bayesian Program Induction

2018-12-01 · Kevin Ellis, Lucas Morales, Mathias Sablé-Meyer, Armando Solar-Lezama 외

Successful approaches to program induction require a hand-engineered domain-specific language (DSL), constraining the space of allowed programs and imparting prior knowledge of the domain. We contribute a program inducti…

Program inductionregressionSymbolic Regression

Learning Libraries of Subroutines for Neurally–Guided Bayesian Program Induction

2018-12-01 · NeurIPS 2018 12 · Kevin Ellis, Lucas Morales, Mathias Sablé-Meyer, Armando Solar-Lezama 외

Successful approaches to program induction require a hand-engineered domain-specific language (DSL), constraining the space of allowed programs and imparting prior knowledge of the domain. We contribute a program …

Program inductionregressionSymbolic Regression

Neurally-Guided Procedural Models: Amortized Inference for Procedural Graphics Programs using Neural Networks

2016-03-19 · NeurIPS 2016 12 · Daniel Ritchie, Anna Thomas, Pat Hanrahan, Noah D. Goodman

Probabilistic inference algorithms such as Sequential Monte Carlo (SMC) provide powerful tools for constraining procedural models in computer graphics, but they require many samples to produce desirable results. In this …

Neurally-Guided Structure Inference

2019-06-17 · Sidi Lu, Jiayuan Mao, Joshua B. Tenenbaum, Jiajun Wu

Most structure inference methods either rely on exhaustive search or are purely data-driven. Exhaustive search robustly infers the structure of arbitrarily complex data, but it is slow. Data-driven methods allow efficien…

Guided Sketch-Based Program Induction by Search Gradients

2024-02-10 · Ahmad Ayaz Amin

Many tasks can be easily solved using machine learning techniques. However, some tasks cannot readily be solved using statistical models, requiring a symbolic approach instead. Program induction is one of the ways that s…

Program induction