34 citations · 50 across the 8 of their papers we have counts for
7 papers · 1 filter
Path-independent Flow Matching for Multi-parameter Generative Dynamics
Francisco Téllez, AmirHossein Zamani, Philippe Martin +5
Flow Matching is a powerful framework for learning transport maps between probability distributions. Yet its standard single-parameter formulation is not designed to capture multi-…
Geometry-Aware Generative Autoencoders for Warped Riemannian Metric Learning and Generative Modeling on Data Manifolds
Xingzhi Sun, Danqi Liao, Kincaid MacDonald +7
Rapid growth of high-dimensional datasets in fields such as single-cell RNA sequencing and spatial genomics has led to unprecedented opportunities for scientific discovery, but it…
AdaFisher: Adaptive Second Order Optimization via Fisher Information
Damien Martins Gomes, Yanlei Zhang, Eugene Belilovsky +2
First-order optimization methods are currently the mainstream in training deep neural networks (DNNs). Optimizers like Adam incorporate limited curvature information by employing t…
DYMAG: Rethinking Message Passing Using Dynamical-systems-based Waveforms
Dhananjay Bhaskar, Xingzhi Sun, Yanlei Zhang +8
We present DYMAG, a graph neural network based on a novel form of message aggregation. Standard message-passing neural networks, which often aggregate local neighbors via mean-aggr…
Simulation-free Schrödinger bridges via score and flow matching
Alexander Tong, Nikolay Malkin, Kilian Fatras +5
We present simulation-free score and flow matching ([SF]M), a simulation-free objective for inferring stochastic dynamics given unpaired samples drawn from arbitrary source and…
A Heat Diffusion Perspective on Geodesic Preserving Dimensionality Reduction
Guillaume Huguet, Alexander Tong, Edward De Brouwer +4
Diffusion-based manifold learning methods have proven useful in representation learning and dimensionality reduction of modern high dimensional, high throughput, noisy datasets. Su…
Improving and generalizing flow-based generative models with minibatch optimal transport
Alexander Tong, Kilian Fatras, Nikolay Malkin +5
Continuous normalizing flows (CNFs) are an attractive generative modeling technique, but they have been held back by limitations in their simulation-based maximum likelihood traini…