Memory-Based Meta-Learning on Non-Stationary Distributions
Tim Genewein,u00a0Gregoire Deletang,u00a0Anian Ruoss,u00a0Li Kevin Wenliang,u00a0Elliot Catt,u00a0Vincent Dutordoir,u00a0Jordi Grau-Moya,u00a0Laurent Orseau,u00a0Marcus Hutter,u00a0Joel Veness
Memory-based meta-learning is a technique for approximating Bayes-optimal predictors. Under fairly general conditions, minimizing sequential prediction error, measured by the log loss, leads to implicit meta-learning. The goal of this work is to investigate how far this interpretation can be realized by current sequence prediction models and training regimes. The focus is on piecewise stationary sources with unobserved switching-points, which arguably capture an important characteristic of natural language and action-observation sequences in partially observable environments. We show that various types of memory-based neural models, including Transformers, LSTMs, and RNNs can learn to accurately approximate known Bayes-optimal algorithms and behave as if performing Bayesian inference over the latent switching-points and the latent parameters governing the data distribution within each segment.
