Transformers are Provably Optimal In-context Estimators for Wireless Communications

arXiv:2311.00226v3 Announce Type: replace-cross
Abstract: Pre-trained transformers exhibit the capability of adapting to new tasks through in-context learning (ICL), where they efficiently utilize a limited set of prompts without explicit model optimization.
The canonical communication problem of estimating transmitted symbols from received observations can be modelled as an in-context learning problem: Received observations are essentially a noisy function of transmitted symbols, and this function can be represented by an unknown parameter whose statistics depend on an (also unknown) latent context. …

abstract arxiv canonical capability communication communications context context learning cs.lg eess.sp in-context learning model optimization optimization problem prompts replace set tasks through transformers type wireless wireless communications