In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization

arXiv:2402.14951v1 Announce Type: cross
Abstract: We study the \emph{in-context learning} (ICL) ability of a \emph{Linear Transformer Block} (LTB) that combines a linear attention component and a linear multi-layer perceptron (MLP) component. For ICL of linear regression with a Gaussian prior and a \emph{non-zero mean}, we show that LTB can achieve nearly Bayes optimal ICL risk. In contrast, using only linear attention must incur an irreducible additive approximation error. Furthermore, we establish a correspondence between LTB and one-step gradient descent estimators …

abstract arxiv attention benefits block context cs.cl cs.lg in-context learning layer linear linear regression mean mlp perceptron prior regression stat.ml study transformer type