Research
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.

169,181 papers · 148 categories

Trend · papers per month

132263395526 · Jun 202019922001200920182026
48 results for Sinkhorn Policy Gradient

SPG learns policies on permutation matrices using Sinkhorn layers.

problem Optimizing permutations for tasks like sorting, ranking, and matching.
method Introduces Sinkhorn Policy Gradient (SPG) algorithm with a temperature-controlled Sinkhorn layer.
result SPG agents perform competitively and are more data-efficient than baseline methods on matching tasks.

The Sinkhorn flow converges to a Wasserstein mirror gradient flow from the Sinkhorn algorithm.

problem Optimizing joint distributions using the Sinkhorn algorithm.
method Wasserstein mirror gradient flow derived from the Sinkhorn algorithm.
result The Sinkhorn flow converges to a Wasserstein mirror gradient flow.

Paper solves barycenter of probability distributions using Sinkhorn divergence.

problem Computing the barycenter of a set of probability distributions under the Sinkhorn divergence.
method Recast as unconstrained functional optimization and develop Sinkhorn Descent (SD) method.
result SD converges to a stationary point at a sublinear rate and asymptotically finds a global minimizer.

New framework optimizes decisions under uncertainty considering causal and continuous data.

problem Optimizing decisions under uncertain distributions with causal and continuous data structures.
method Developed a framework using Causal Sinkhorn DRO with Soft Regression Forest decision rules.
result Framework provides interpretable and tractable decision rules for optimizing under uncertainty.

New insights into Sinkhorn approximation's smoothness and differentiation.

problem Lack of accurate and differentiable approximation of Wasserstein distance.
method Characterized differential properties of Sinkhorn distance and provided an efficient gradient algorithm.
result The original Sinkhorn distance is as smooth as its regularized version, enabling better learning and optimization.

The paper analyzes stability and convergence rates of entropic and Sinkhorn potentials.

problem Stability and convergence rates of entropic and Sinkhorn potentials.
method Semiconcavity properties of entropic potentials and Schrödinger bridges.
result Exponential convergence rates for gradient and Hessian of Sinkhorn iterates.

Paper analyzes convergence of Sinkhorn algorithm for discrete probability measures on torus.

problem Achieving exponential convergence of Sinkhorn algorithm in general settings.
method Coupling by reflection techniques for controlled diffusions on the torus.
result Proves pointwise exponential convergence of Sinkhorn iterates and their gradient.

This paper tackles Sinkhorn DRO by reformulating it as a bilevel program and proposes sampling-based algorithms.

problem Distributionally robust optimization with ambiguity sets defined via the Sinkhorn discrepancy.
method Primal perspective reformulation as a bilevel program, double-loop and single-loop sampling-based algorithms.
result Simultaneously obtain the optimal robust decision and the worst-case distribution.

A new associative memory uses Sinkhorn divergence for efficient pattern retrieval.

problem Efficiently retrieving patterns from large datasets of weighted point clouds.
method Derived retrieval dynamics as a SHK gradient flow, discretized for a deterministic algorithm.
result Proved basin invariance, geometric convergence, and robust recovery from perturbations.

New algorithm solves Schrödinger bridge problem with mismatched channels.

problem Solving Schrödinger bridge problem with input and noise channel mismatch.
method Design of a Sinkhorn recursion with memory for nonlinear PDEs.
result Demonstrates solving control-affine Schrödinger bridge problem.

It is of increasing importance to develop learning methods for ranking. In contrast to many learning objectives, however, the ranking problem presents difficulties due to the fact that the space of permutations is not smooth. In this paper, we examine the class of rank-linear objective functions, which includes popular…

2011-06-09abs ↗pdf ↗

Paper tackles robust model training with a new stochastic algorithm.

problem Training robust models against data distribution shift.
method Derives a novel dual formulation and proposes a nested stochastic gradient descent algorithm.
result Establishes polynomial iteration and sample complexities for large-scale DRO problems.

A new gradient flow framework for distributionally robust optimization.

problem Optimizing under uncertainty with worst-case distributional constraints.
method Gradient flow theory applied to distributionally robust optimization.
result Practical algorithms for sampling from worst-case distributions.

New discretization scheme for Wasserstein gradient flows using Schrödinger bridges.

problem Computing Wasserstein gradient flows efficiently and without score functions.
method Iterated Schrödinger bridge approximation with particle-based Sinkhorn algorithm.
result The scheme converges to Wasserstein gradient flows for certain flows, including heat flow.

A new algorithm screens negligible components to efficiently approximate optimal transport distances.

problem Efficiently approximating the Sinkhorn distance between discrete measures.
method Screening of negligible components in the dual solution of the regularized Sinkhorn problem.
result Screenkhorn algorithm provides provable guarantees with smaller computational complexity.

Improved Sinkhorn algorithm for UOT with near-linear complexity.

problem Solving the entropic regularized Unbalanced Optimal Transport problem efficiently.
method Geometric convergence analysis of Sinkhorn updates and primal solution properties.
result Near-linear time complexity for finding ε\varepsilon-approximate UOT solutions.

This paper introduces Gumbel-Sinkhorn networks for learning latent matchings.

problem Learning in latent variable models with permutations is difficult due to combinatorial intractability.
method Approximates maximum-weight matching using the Sinkhorn operator, extending Gumbel-Softmax.
result Demonstrates effectiveness on sorting, jigsaw puzzles, and neural signal identification tasks.

This work studies the statistical performance of Sinkhorn iterations in estimating Schrödinger bridges.

problem Estimating Schrödinger bridges with limited samples.
method Intermediate Sinkhorn iterations applied to the time-dependent drifts of SDEs.
result Established a statistical bound on the squared total variation error of Sinkhorn bridge iterations.

Paper uses Sinkhorn distances to improve imitation learning effectiveness.

problem Improving imitation learning algorithms by comparing occupancy measures.
method Formulates imitation learning as Sinkhorn distance minimization, combining optimal transport and cosine distances.
result Proposes a new critic network and transport plan that guide imitation learning.

This paper refines the Gaussian Sinkhorn algorithm for general multivariate models.

problem Finite-dimensional solutions for general Gaussian multivariate models.
method Recursive formulation of the Sinkhorn algorithm for Gaussian models, including closed form expressions of entropic transport maps and Schrödinger bridges.
result Refined convergence analysis of Gaussian Sinkhorn algorithms.

This paper generalizes Sinkhorn algorithm for unbalanced optimal transport.

problem Handling distributions with different total mass and robustness to outliers.
method Alternates between standard Sinkhorn updates and pointwise application of a contractive function.
result Defines Sinkhorn divergences that are differentiable, positive, definite, convex, and robust.

OTSeg uses multi-prompt Sinkhorn attention to improve zero-shot semantic segmentation.

problem Leveraging pre-trained CLIP knowledge to align text embeddings with pixel embeddings.
method OTSeg employs Multi-Prompts Sinkhorn (MPS) and Multi-Prompts Sinkhorn Attention (MPSA) to enhance semantic feature matching.
result OTSeg achieves state-of-the-art performance in zero-shot semantic segmentation tasks.

Develops a new algorithm to calibrate signed datasets to specified marginals.

problem Calibrating signed datasets to specified marginals.
method Extends Schrödinger-Fortet-Sinkhorn paradigm to sign-indefinite multi-dimensional arrays.
result Proposes an optimization problem to update a sign-indefinite prior to match given marginals.

Study convergence and approximations of entropic regularized Wasserstein distances for Gaussian and RKHS measures.

problem Convergence and approximations of entropic regularized Wasserstein distances in Gaussian and RKHS settings.
method Analysis of convergence and finite sample approximations of entropic regularized Wasserstein distances in Gaussian and RKHS settings.
result Strictly weaker convergence in 2-Sinkhorn divergence for Gaussian measures compared to exact 2-Wasserstein distance.

W-Flow generates images in one step, faster and better than multi-step methods.

problem Efficiently generating images from a simple reference distribution to a target data distribution.
method W-Flow uses Wasserstein gradient flows to transform the reference distribution to the target distribution in a single step, trained with Sinkhorn divergence.
result W-Flow achieves state-of-the-art results in ImageNet 256imes imes256 generation with improved mode coverage and faster sampling.

Paper proposes SinkhornDRL for distributional RL using Sinkhorn divergence and regularized Wasserstein loss.

problem Improving distributional reinforcement learning by minimizing Bellman return distribution differences.
method Introduces SinkhornDRL, a distributional RL algorithm using Sinkhorn divergence and regularized Wasserstein loss.
result SinkhornDRL consistently outperforms or matches existing algorithms on Atari games, especially in multi-dimensional reward settings.

Optimal transport with ff-divergence regularization using generalized Sinkhorn algorithm.

problem Optimal transport with ff-divergence regularization.
method Generalized Sinkhorn algorithm for solving optimal transport problems with various ff-divergences.
result Strong duality holds, optimums are attained, and convergence to an optimal solution is guaranteed under certain conditions.