Search Results for author:
Found 16 papers, 10 papers with code
Geometry-Aware Generative Autoencoders for Warped Riemannian Metric Learning and Generative Modeling on Data Manifolds
GAGA constructs a neural network embedding space that respects the intrinsic geometries discovered by manifold learning and learns a novel warped Riemannian metric on the data space.
ImageFlowNet: Forecasting Multiscale Image-Level Trajectories of Disease Progression with Irregularly-Sampled Longitudinal Medical Images
We validate ImageFlowNet on three longitudinal medical image datasets depicting progression in geographic atrophy, multiple sclerosis, and glioblastoma, demonstrating its ability to effectively forecast disease progression and outperform existing methods.
Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Backbone Generation
Proteins are essential for almost all biological processes and derive their diverse functions from complex 3D structures, which are in turn determined by their amino acid sequences.
Assessing Neural Network Representations During Training Using Noise-Resilient Diffusion Spectral Entropy
Entropy and mutual information in neural networks provide rich information on the learning process, but they have proven difficult to compute reliably in high dimensions.
SE(3)-Stochastic Flow Matching for Protein Backbone Generation
The computational design of novel protein structures has the potential to impact numerous scientific disciplines greatly.
Simulation-free Schrödinger bridges via score and flow matching
We present simulation-free score and flow matching ([SF]$^2$M), a simulation-free objective for inferring stochastic dynamics given unpaired samples drawn from arbitrary source and target distributions.
Graph Fourier MMD for Signals on Graphs
GFMMD is defined via an optimal witness function that is both smooth on the graph and maximizes difference in expectation between the pair of distributions on the graph.
Neural FIM for learning Fisher Information Metrics from point cloud data
Although data diffusion embeddings are ubiquitous in unsupervised learning and have proven to be a viable technique for uncovering the underlying intrinsic geometry of data, diffusion embeddings are inherently limited due to their discrete nature.
Assessing Neural Network Representations During Training Using Data Diffusion Spectra
We also see that there is an increase in DSMI with the class label over time.
A Heat Diffusion Perspective on Geodesic Preserving Dimensionality Reduction
Finally, we show that parameters of our more general method can be configured to give results similar to PHATE (a state-of-the-art diffusion based manifold learning method) as well as SNE (an attraction/repulsion neighborhood based method that forms the basis of t-SNE).
Improving and generalizing flow-based generative models with minibatch optimal transport
CFM features a stable regression objective like that used to train the stochastic flow in diffusion models but enjoys the efficient inference of deterministic flow models.
Geodesic Sinkhorn for Fast and Accurate Optimal Transport on Manifolds
Efficient computation of optimal transport distance between distributions is of growing importance in data science.
Manifold Interpolating Optimal-Transport Flows for Trajectory Inference
In GAE the latent space distance between points is regularized to match a novel multiscale geodesic distance on the data manifold that we define.
Time-inhomogeneous diffusion geometry and topology
From a geometric perspective, we obtain convergence bounds based on the smallest transition probability and the radius of the data, whereas from a spectral perspective, our bounds are based on the eigenspectrum of the diffusion kernel.
Embedding Signals on Knowledge Graphs with Unbalanced Diffusion Earth Mover's Distance
We propose to compare and organize such datasets of graph signals by using an earth mover's distance (EMD) with a geodesic cost over the underlying graph.
Diffusion Earth Mover's Distance and Distribution Embeddings
Here, Diffusion EMD can derive distances between patients on the manifold of cells at least two orders of magnitude faster than equally accurate methods.
