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.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

11 results for “Wasserstein-proximal”

Preconditioned Regularized Wasserstein Proximal Samplingstat.ML

New sampling method using regularized Wasserstein proximal for Gibbs distributions.

problem Sampling from Gibbs distributions with numerical stability and efficiency.

method Preconditioned regularized Wasserstein proximal operator.

result Discrete-time convergence analysis and explicit bias characterization.

sampling Gibbs distribution Wasserstein proximal preconditioning heat equations

2025-09-01abs ↗pdf ↗

Accelerated Regularized Wasserstein Proximal Sampling Algorithmsstat.ML

Accelerates sampling from Gibbs distributions using ARWP method.

problem Sampling from Gibbs distributions efficiently.

method ARWP method, combining Nesterov acceleration and regularized Wasserstein proximal.

result ARWP exhibits higher contraction rate and faster tail exploration.

sampling Gibbs distribution ARWP acceleration Wasserstein proximal

2026-01-14abs ↗pdf ↗

Noise-Free Sampling Algorithms via Regularized Wasserstein Proximalsstat.ML

Noise-free sampling method using Wasserstein proximal for faster convergence.

problem Sampling from distributions governed by potential functions.

method Deterministic score-based MCMC with regularized Wasserstein proximal.

result Improved mixing time bounds for Gaussian distributions compared to ULA and MALA.

sampling algorithms MCMC Wasserstein proximal fast convergence Bayesian logistic regression

2023-08-28abs ↗pdf ↗

Sparse Transformer Architectures via Regularized Wasserstein Proximal Operator with

L_1

Priorcs.LG

Sparse transformer architecture improves accuracy and speed in generative modeling and inverse problems.

problem Improving accuracy and speed in generative modeling and inverse problems.

method Proposes a sparse transformer architecture using regularized Wasserstein proximal operator with

L_1

prior.

result Sparse transformer achieves higher accuracy and faster convergence than classical methods.

sparse transformer Wasserstein proximal L1 regularization generative modeling inverse problems

2025-10-18abs ↗pdf ↗

Improved analysis for a proximal algorithm for samplingmath.ST

Improved sampling guarantees for weakly log-concave distributions.

problem Sampling from distributions that are not strongly log-concave.

method Proximal sampler with convergence guarantees under weaker assumptions.

result New state-of-the-art sampling guarantees for various target distributions.

sampling log-concave weakly log-concave convergence Wasserstein

2022-02-13abs ↗pdf ↗

Wasserstein proximal operators describe score-based generative models and resolve memorizationstat.ML

Mathematical analysis improves SGMs, resolving memorization issues.

problem Improving performance and avoiding memorization in SGMs.

method Formulated SGMs using Wasserstein proximal operators and mean-field games.

result Improved SGM performance in terms of training samples and time.

Score-based generative models Wasserstein proximal operators Memorization effects Mean-field games Interpretable kernels

2024-02-09abs ↗pdf ↗

Learning Concave Bid Shading Strategies in Online Auctions via Measure-valued Proximal Optimizationcs.LG

This work optimizes bid strategies for online auctions using measure-valued optimization.

problem Optimizing bid strategies in first-price auctions to maximize expected surplus.

method Formulates the problem as convex optimization over the joint distribution of shading parameters, adapts the distribution after each auction using a Wasserstein-proximal update.

result The proposed algorithm encourages bids on values with high expected surplus.

online auctions bid shading measure-valued optimization convex optimization Wasserstein-proximal

2025-09-12abs ↗pdf ↗

Combining Wasserstein-1 and Wasserstein-2 proximals: robust manifold learning via well-posed generative flowsstat.ML

Generative flows learn distributions on low-dimensional manifolds robustly via Wasserstein proximals.

problem Learning distributions supported on low-dimensional manifolds robustly.

method Combining Wasserstein-1 and Wasserstein-2 proximal operators to formulate well-posed continuous-time generative flows.

result The combination of Wasserstein-1 and Wasserstein-2 proximals ensures the well-posedness of generative flows, leading to unique and robust learning.

Generative flows Wasserstein proximal Mean-field game Optimal transport Low-dimensional manifolds

2024-07-16abs ↗pdf ↗

Convergence Analysis of the Wasserstein Proximal Algorithm beyond Geodesic Convexitymath.OC

Paper analyzes convergence of proximal algorithm in metric spaces without geodesic convexity.

problem Analyzing convergence of proximal algorithm in general metric spaces.

method Analysis of the Wasserstein proximal algorithm without geodesic convexity assumption.

result Establishes unbiased and linear convergence rate for proximal algorithm under natural Wasserstein inequality.

proximal algorithm convergence analysis metric spaces Wasserstein geodesic convexity

2025-01-25abs ↗pdf ↗

Flow-based Distributionally Robust Optimizationcs.LG

A new framework solves complex optimization problems with continuous worst-case distributions.

problem Optimizing under uncertain distributions with continuous worst-case scenarios.

method Flow-based distributionally robust optimization (DRO) with Wasserstein uncertainty sets and invertible transport maps.

result The framework finds continuous worst-case distributions and samples efficiently.

Distributionally Robust Optimization Flow-based Models Wasserstein Proximal Gradient Flow Continuous-Time Invertible Maps Adversarial Learning

2023-10-30abs ↗pdf ↗

The Wasserstein Proximal Gradient Algorithmmath.OC

A new algorithm for minimizing functions on Wasserstein space.

problem Discretization of continuous Wasserstein gradient flows in machine learning.

method Forward-Backward discretization scheme for minimizing functions with smooth and nonsmooth components.

result The FB scheme converges similarly to proximal gradient algorithms in Euclidean spaces.

Wasserstein space optimal transport convex optimization machine learning discretization

2020-02-07abs ↗pdf ↗