A generative transfer framework using iterative path-wise tilting integrated with conditional flow matching recovers target entropic optimal transport couplings from reference samples, achieving O(δ) convergence in Wasserstein-1 distance.
Sliced and radon wasserstein barycenters of measures,
10 Pith papers cite this work, alongside 310 external citations. Polarity classification is still indexing.
10
Pith papers citing it
310
external citations · Crossref
years
2026 10verdicts
UNVERDICTED 10representative citing papers
Tempered Guided Diffusion uses annealed SMC to produce consistent particle approximations to the posterior for training-free conditional diffusion sampling, outperforming independent guided trajectories in experiments.
An intrinsic effective sample size for manifold MCMC is defined via kernel discrepancy as the number of independent draws yielding equivalent expected squared discrepancy to the target.
The profile maximum likelihood estimator for the location in anisotropic hyperbolic wrapped normal models is strongly consistent, asymptotically normal, and attains the Hájek-Le Cam minimax lower bound under squared geodesic loss.
Introduces BRIDGE and SKFM algorithms that detect latent confounders via non-closing Lie brackets in interventional vector fields derived from density ratios.
FLaG is a frequency-domain module using FFT, latent queries, and gating that improves token aggregation and shows gains on ESM2 AMP prediction and CIFAR-100 image classification while staying competitive on text tasks.
Introduces PEMS W and two CorSW discrepancies on full-rank correlation matrices to improve domain generalization in EEG decoding under distribution shifts.
Random slicing for subsampling combined with Nadaraya-Watson smoothing enables faster and improved persistence-based topological optimization of point clouds in 2D and 3D.
Joint location-scale minimization for geometric medians on product manifolds degenerates to marginal medians, and three new scale-selection methods restore identifiability with asymptotic guarantees.
A method that runs static traffic assignment on hypothetical demand for each road network and compares the resulting traffic-weighted geographic distributions via 2D Wasserstein distance.
citing papers explorer
-
Generative Transfer for Entropic Optimal Transport with Unknown Costs
A generative transfer framework using iterative path-wise tilting integrated with conditional flow matching recovers target entropic optimal transport couplings from reference samples, achieving O(δ) convergence in Wasserstein-1 distance.
-
Tempered Guided Diffusion
Tempered Guided Diffusion uses annealed SMC to produce consistent particle approximations to the posterior for training-free conditional diffusion sampling, outperforming independent guided trajectories in experiments.
-
Intrinsic effective sample size for manifold-valued Markov chain Monte Carlo via kernel discrepancy
An intrinsic effective sample size for manifold MCMC is defined via kernel discrepancy as the number of independent draws yielding equivalent expected squared discrepancy to the target.
-
Profile Likelihood Inference for Anisotropic Hyperbolic Wrapped Normal Models on Hyperbolic Space
The profile maximum likelihood estimator for the location in anisotropic hyperbolic wrapped normal models is strongly consistent, asymptotically normal, and attains the Hájek-Le Cam minimax lower bound under squared geodesic loss.
-
Latent Confounded Causal Discovery via Lie Bracket Geometry
Introduces BRIDGE and SKFM algorithms that detect latent confounders via non-closing Lie brackets in interventional vector fields derived from density ratios.
-
Frequency-Domain Latent Attention Gating for Cross-Domain Token Aggregation
FLaG is a frequency-domain module using FFT, latent queries, and gating that improves token aggregation and shows gains on ESM2 AMP prediction and CIFAR-100 image classification while staying competitive on text tasks.
-
A Sliced-Wasserstein Framework on Correlation Matrices for EEG Decoding
Introduces PEMS W and two CorSW discrepancies on full-rank correlation matrices to improve domain generalization in EEG decoding under distribution shifts.
-
Towards Scalable Persistence-Based Topological Optimization
Random slicing for subsampling combined with Nadaraya-Watson smoothing enables faster and improved persistence-based topological optimization of point clouds in 2D and 3D.
-
Scale selection for geometric medians on product manifolds
Joint location-scale minimization for geometric medians on product manifolds degenerates to marginal medians, and three new scale-selection methods restore identifiability with asymptotic guarantees.
-
Distance between Road Networks: A Macroscopic Method for Road Network Datasets Comparison Using Traffic-weighted Geographic Distribution
A method that runs static traffic assignment on hypothetical demand for each road network and compares the resulting traffic-weighted geographic distributions via 2D Wasserstein distance.