6 papers · 1 filter
Few-Step Boltzmann Generators via Scalable Likelihood Flow Maps
RuiKang OuYang, Hanlin Yu, Xinyue Ai +7
Recent progress in flow-based generative modeling has led to models that output high-quality samples while using only a small number of function evaluations. However, at present, t…
Connecting Neural Models Latent Geometries with Relative Geodesic Representations
Hanlin Yu, Berfin Inal, Georgios Arvanitidis +3
Neural models learn representations of high-dimensional data on low-dimensional manifolds. Multiple factors, including stochasticities in the training process, model architectures,…
Learning Geometry and Topology via Multi-Chart Flows
Hanlin Yu, Søren Hauberg, Marcelo Hartmann +2
Real world data often lie on low-dimensional Riemannian manifolds embedded in high-dimensional spaces. This motivates learning degenerate normalizing flows that map between the amb…
Geodesic Slice Sampler for Multimodal Distributions with Strong Curvature
Bernardo Williams, Hanlin Yu, Hoang Phuc Hau Luu +2
Traditional Markov Chain Monte Carlo sampling methods often struggle with sharp curvatures, intricate geometries, and multimodal distributions. Slice sampling can resolve local exp…
Density Ratio Estimation with Conditional Probability Paths
Hanlin Yu, Arto Klami, Aapo Hyvärinen +2
Density ratio estimation in high dimensions can be reframed as integrating a certain quantity, the time score, over probability paths which interpolate between the two densities. I…
Stochastic variance-reduced Gaussian variational inference on the Bures-Wasserstein manifold
Hoang Phuc Hau Luu, Hanlin Yu, Bernardo Williams +2
Optimization in the Bures-Wasserstein space has been gaining popularity in the machine learning community since it draws connections between variational inference and Wasserstein g…