10 papers
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…
Learning Energy-Based Models from Stochastic Interpolants using Spatiotemporal Differences
Hanlin Yu, RuiKang OuYang, Partha Kaushik +3
Learning an energy-based model from data samples is a central problem in machine learning. Many recent and popular methods, such as denoising score matching for training energy-bas…
PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation
Junru Zhang, Lang Feng, Jinbo Wang +6
Generating high-quality time-series data is challenging because real-world signals often exhibit multimodal patterns and multiscale dynamics, including oscillations and high-freque…
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…
Riemannian Laplace Approximation with the Fisher Metric
Hanlin Yu, Marcelo Hartmann, Bernardo Williams +2
Laplace's method approximates a target density with a Gaussian distribution at its mode. It is computationally efficient and asymptotically exact for Bayesian inference due to the…
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,…