Two stage machine learning based channel state feedback

A user equipment (UE) for wireless communications, comprising:

• one or more memories storing processor-executable code;
• and
• one or more processors coupled with the one or more memories and individually or collectively operable to execute the code to cause the UE to:
• select a non-Discrete Fourier Transform (non-DFT) codebook of a set of non-DFT codebooks associated with a channel state feedback message;
• determine a set of singular vectors associated with the non-DFT codebook based at least in part on a first machine learning model, wherein the set of singular vectors corresponds to a subspace associated with the non-DFT codebook;
• compress the non-DFT codebook, the set of singular vectors, or both, based at least in part on a second machine learning model;
• and
• transmit the channel state feedback message comprising the compressed non-DFT codebook, the compressed set of singular vectors, or both.