exponential map
Neural Latent Geometry Search: Product Manifold Inference via Gromov-Hausdorff-Informed Bayesian Optimization Haitz Sรกez de Ocรกriz Borde Oxford Robotics Institute University of Oxford รlvaro Arroyo
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.
Riemannian Laplace approximations for Bayesian neural networks
However, practical posteriors are often, even locally, highly non-Gaussian, and empirical performance deteriorates.
de7858e3e7f9f0f7b2c7bfdc86f6d928-Supplemental-Conference.pdf
Inourexperiments, we visualize images for the mini-ImageNet dataset, and thus we utilize the image generator from the work [10] asG, which is pre-trained on ImageNet, and we pre-trainf on the mini-ImageNet dataset.
Escaping from saddle points on Riemannian manifolds
Yue Sun, Nicolas Flammarion, Maryam Fazel
Neural Information Processing Systems http://nips.cc/
