Neural Latent Geometry Search: Product Manifold Inference via Gromov-Hausdorff-Informed Bayesian Optimization Haitz Sáez de Ocáriz Borde Oxford Robotics Institute University of Oxford Álvaro Arroyo

Feb-15-2026, 01:51:46 GMT–Neural Information Processing Systems 

Recent research indicates that the performance of machine learning models can be improved by aligning the geometry of the latent space with the underlying data structure.