Learning Universal Predictors

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Grau-Moya, Jordi, Genewein, Tim, Hutter, Marcus, Orseau, Laurent, Delétang, Grégoire, Catt, Elliot, Ruoss, Anian, Wenliang, Li Kevin, Mattern, Christopher, Aitchison, Matthew, Veness, Joel
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916106758782976
author Grau-Moya, Jordi
Genewein, Tim
Hutter, Marcus
Orseau, Laurent
Delétang, Grégoire
Catt, Elliot
Ruoss, Anian
Wenliang, Li Kevin
Mattern, Christopher
Aitchison, Matthew
Veness, Joel
author_facet Grau-Moya, Jordi
Genewein, Tim
Hutter, Marcus
Orseau, Laurent
Delétang, Grégoire
Catt, Elliot
Ruoss, Anian
Wenliang, Li Kevin
Mattern, Christopher
Aitchison, Matthew
Veness, Joel
contents Meta-learning has emerged as a powerful approach to train neural networks to learn new tasks quickly from limited data. Broad exposure to different tasks leads to versatile representations enabling general problem solving. But, what are the limits of meta-learning? In this work, we explore the potential of amortizing the most powerful universal predictor, namely Solomonoff Induction (SI), into neural networks via leveraging meta-learning to its limits. We use Universal Turing Machines (UTMs) to generate training data used to expose networks to a broad range of patterns. We provide theoretical analysis of the UTM data generation processes and meta-training protocols. We conduct comprehensive experiments with neural architectures (e.g. LSTMs, Transformers) and algorithmic data generators of varying complexity and universality. Our results suggest that UTM data is a valuable resource for meta-learning, and that it can be used to train neural networks capable of learning universal prediction strategies.
format Preprint
id arxiv_https___arxiv_org_abs_2401_14953
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning Universal Predictors
Grau-Moya, Jordi
Genewein, Tim
Hutter, Marcus
Orseau, Laurent
Delétang, Grégoire
Catt, Elliot
Ruoss, Anian
Wenliang, Li Kevin
Mattern, Christopher
Aitchison, Matthew
Veness, Joel
Machine Learning
Artificial Intelligence
Meta-learning has emerged as a powerful approach to train neural networks to learn new tasks quickly from limited data. Broad exposure to different tasks leads to versatile representations enabling general problem solving. But, what are the limits of meta-learning? In this work, we explore the potential of amortizing the most powerful universal predictor, namely Solomonoff Induction (SI), into neural networks via leveraging meta-learning to its limits. We use Universal Turing Machines (UTMs) to generate training data used to expose networks to a broad range of patterns. We provide theoretical analysis of the UTM data generation processes and meta-training protocols. We conduct comprehensive experiments with neural architectures (e.g. LSTMs, Transformers) and algorithmic data generators of varying complexity and universality. Our results suggest that UTM data is a valuable resource for meta-learning, and that it can be used to train neural networks capable of learning universal prediction strategies.
title Learning Universal Predictors
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2401.14953