Transformers are Minimax Optimal Nonparametric In-Context Learners
This provides foundational theoretical insights into why in-context learning works, which is important for researchers in machine learning and AI.
The paper tackled the theoretical understanding of in-context learning in transformers by analyzing their approximation and generalization errors for nonparametric regression tasks, showing that sufficiently trained transformers can achieve or improve upon minimax optimal estimation risk.
In-context learning (ICL) of large language models has proven to be a surprisingly effective method of learning a new task from only a few demonstrative examples. In this paper, we study the efficacy of ICL from the viewpoint of statistical learning theory. We develop approximation and generalization error bounds for a transformer composed of a deep neural network and one linear attention layer, pretrained on nonparametric regression tasks sampled from general function spaces including the Besov space and piecewise $γ$-smooth class. We show that sufficiently trained transformers can achieve -- and even improve upon -- the minimax optimal estimation risk in context by encoding the most relevant basis representations during pretraining. Our analysis extends to high-dimensional or sequential data and distinguishes the \emph{pretraining} and \emph{in-context} generalization gaps. Furthermore, we establish information-theoretic lower bounds for meta-learners w.r.t. both the number of tasks and in-context examples. These findings shed light on the roles of task diversity and representation learning for ICL.