Abstract: Implementations disclose selecting, in response to receiving a generative model request and from among multiple candidate generative models, a particular generative model to utilize in generating a response to the generative model request. Various implementations identify an indication of a submitting entity of the generative model request. The particular generative model can be selected based on processing the generative model request and custom selection feature(s) provided by the submitting entity (e.g., provided well in advance of the generative model request). Different submitting entities (e.g., a first and second entities) can have different custom selection features. Accordingly, even if the first and second submitting entities submit the same generative model request, different generative models are selected to process the generative model request, resulting in two different responses, one responsive to the first entity and the other responsive to the second entity.

Abstract: A sparse dataset is encoded using a data-driven learned sensing matrix. For example, an example method includes receiving a dataset of sparse vectors with dimension d from a requesting process, initializing an encoding matrix of dimension k×d, selecting a subset of sparse vectors from the dataset, and updating the encoding matrix via machine learning. Updating the encoding matrix includes using a linear encoder to generate an encoded vector of dimension k for each vector in the subset, the linear encoder using the encoding matrix, using a non-linear decoder to decode each of the encoded vectors, the non-linear decoder using a transpose of the encoding matrix in a projected subgradient, and adjusting the encoding matrix using back propagation. The method also includes returning an embedding of each sparse vector in the dataset of sparse vectors, the embedding being generated with the updated encoding matrix.

Abstract: A sparse dataset is encoded using a data-driven learned sensing matrix. For example, an example method includes receiving a dataset of sparse vectors with dimension d from a requesting process, initializing an encoding matrix of dimension k×d, selecting a subset of sparse vectors from the dataset, and updating the encoding matrix via machine learning. Updating the encoding matrix includes using a linear encoder to generate an encoded vector of dimension k for each vector in the subset, the linear encoder using the encoding matrix, using a non-linear decoder to decode each of the encoded vectors, the non-linear decoder using a transpose of the encoding matrix in a projected subgradient, and adjusting the encoding matrix using back propagation. The method also includes returning an embedding of each sparse vector in the dataset of sparse vectors, the embedding being generated with the updated encoding matrix.