US Patent 11424791 Machine learning model selection in beamformed communications

Methods, systems, and devices for wireless communications are described in which a base station may develop a number of different predictive models for each of a number of different functions. The different functions may be used to determine various beamforming parameters for beamformed communications between a user equipment (UE) and a base station. The base station may provide the models to a UE, and the UE may then use such models to determine values for one or more beamforming parameters. A same function (e.g., a beam prediction function to identify a transmit/receive beam for communications) may have multiple different models, which may be provided to the UE by the base station, which may be used based on particular channel conditions or locations of a UE. The UE or base station may select which model of the multiple predictive models is to be used for communications.