On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “Orlicz-Wasserstein”

Generalized Sobolev Transport for Probability Measures on a Graphstat.ML

Proposes GST for efficient computation of generalized Sobolev transport on graph metrics.

problem Optimal transport for measures on graph metric spaces with limited flexibility.

method Introduces GST, a generalized variant of Sobolev transport that adapts to various geometric structures.

result GST is significantly faster than Orlicz-Wasserstein (OW) and demonstrates advantages in document classification and topological data analysis.

Optimal Transport Graph Metrics Sobolev Transport Orlicz-Wasserstein Graph Classification

2024-02-07abs ↗pdf ↗

On Interpolation and Curvature via Wasserstein Geodesicsmath.DG

In this article, a proof of the interpolation inequality along geodesics in $p$ -Wasserstein spaces is given. This interpolation inequality was the main ingredient to prove the Borel-Brascamp-Lieb inequality for general Riemannian and Finsler manifolds and led Lott-Villani and Sturm to define an abstract Ricci curvature…

2013-11-21abs ↗pdf ↗

Tail-Sensitive KL and Rényi Convergence of Unadjusted Hamiltonian Monte Carlo via One-Shot Couplingsstat.ML

This work improves convergence guarantees for unadjusted HMC in KL and Rényi divergences.

problem Understanding convergence properties of unadjusted HMC in divergences like KL and Rényi.

method One-shot couplings to establish regularization and lift convergence bounds.

result Quantitative control of relative density mismatch and warm-start requirements.

Hamiltonian Monte Carlo KL divergence Rényi divergence Wasserstein convergence One-shot couplings

2026-01-13abs ↗pdf ↗

Generalized Sobolev IPM for Graph-Based Measurescs.LG

Generalizes Sobolev IPM for graph-based measures using Orlicz geometric structure.

problem Limitation of Le et al. (2025) framework to

L^p

geometry.

method Generalizes Sobolev IPM through Orlicz geometric structure, employing convex functions to capture nuanced geometric relationships.

result GSI-M reduces to a simple univariate optimization problem, achieving remarkable computational efficiency.

Sobolev IPM Orlicz geometric structure Graph-based measures Optimal transport Musielak norm

2025-10-29abs ↗pdf ↗

Faster high-accuracy log-concave sampling via algorithmic warm startsmath.ST

Improved log-concave sampling to $O(d^{1/2})$ with warm starts.

problem Sampling from strongly log-concave distributions efficiently.

method Warm starts and discretized underdamped Langevin diffusion.

result Achieved

O(d^{1/2})

complexity for high-accuracy sampling.

sampling log-concave warm starts underdamped Langevin mixing rates

2023-02-20abs ↗pdf ↗

An Efficient Orlicz-Sobolev Approach for Transporting Unbalanced Measures on a Graphstat.ML

A new method for transporting unbalanced measures on graphs efficiently.

problem Optimal transport for measures with unequal total masses on graph metric spaces.

method Developed a novel variant of entropy partial transport (Orlicz-EPT) with Orlicz geometric structure, leading to Orlicz-Sobolev transport (OST).

result OST can be efficiently computed by solving a univariate optimization problem, significantly faster than Orlicz-EPT.

Optimal Transport Unbalanced Measures Graph Metrics Orlicz-Sobolev Efficient Computation

2025-02-02abs ↗pdf ↗