Random rotational embedding Bayesian optimization for human-in-the-loop personalized music generation.

ABSTRACT: Generative deep learning models, such as those used for music generation, can produce a wide variety of results based on perturbations of random points in their latent space. User preferences can be incorporated in the generative process by replacing this random sampling with a personalized query. Bayesian optimization, a sample-efficient nonlinear optimization method, is the gold standard for human-in-the-loop optimization problems, such as finding this query. In this paper, we present random rotational embedding Bayesian optimization (ROMBO). This novel method can efficiently sample and optimize high-dimensional spaces with rotational symmetries, like the Gaussian latent spaces found in generative models. ROMBO works by embedding a low-dimensional Gaussian search space into a high-dimens

SUBMITTER: Marcos M 

PROVIDER: S-EPMC12637961 | biostudies-literature | 2025

REPOSITORIES: biostudies-literature