paper-with-me

홈 › Papers

Learning Universal Predictors

2024-01-26 · Jordi Grau-Moya, Tim Genewein, Marcus Hutter, Laurent Orseau, Grégoire Delétang, Elliot Catt, Anian Ruoss, Li Kevin Wenliang, Christopher Mattern, Matthew Aitchison, Joel Veness

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.

📄 PDF Abstract BibTeX arXiv:2401.14953

Code (1)

google-deepmind/neural_networks_solomonoff_induction 공식 구현 jax

Tasks

Meta-Learning

Similar Papers 제목 키워드 기반

Universality of conformal prediction under the assumption of randomness

2025-02-26 · Vladimir Vovk

Conformal predictors provide set or functional predictions that are valid under the assumption of randomness, i.e., under the assumption of independent and identically distributed data. The question asked in this paper i…

Conformal PredictionPredictionregressionvalid

Batch Universal Prediction

2024-02-06 · Marco Bondaschi, Michael Gastpar

Large language models (LLMs) have recently gained much popularity due to their surprising ability at generating human-like English sentences. LLMs are essentially predictors, estimating the probability of a sequence of w…

Prediction

Transformers are Universal Predictors

2023-07-15 · Sourya Basu, Moulik Choraria, Lav R. Varshney

We find limits to the Transformer architecture for language modeling and show it has a universal prediction property in an information-theoretic sense. We further analyze performance in non-asymptotic data regimes to und…

Language ModelingLanguage Modelling

Universal time-series forecasting with mixture predictors

2020-10-01 · Daniil Ryabko

This book is devoted to the problem of sequential probability forecasting, that is, predicting the probabilities of the next outcome of a growing sequence of observations given the past. This problem is considered in a v…

Time SeriesTime Series AnalysisTime Series Forecasting

Accidental exploration through value predictors

· Tomasz Kisielewski, Damian Leśniak, Maia Pasek

Infinite length of trajectories is an almost universal assumption in the theoretical foundations of reinforcement learning. In practice learning occurs on finite trajectories. In this paper we examine a specific result o…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)