paper-with-me

홈 › Papers

Sinkhorn Distances: Lightspeed Computation of Optimal Transport

2013-12-01 · NeurIPS 2013 12 · Marco Cuturi

Optimal transportation distances are a fundamental family of parameterized distances for histograms in the probability simplex. Despite their appealing theoretical properties, excellent performance and intuitive formulation, their computation involves the resolution of a linear program whose cost is prohibitive whenever the histograms' dimension exceeds a few hundreds. We propose in this work a new family of optimal transportation distances that look at transportation problems from a maximum-entropy perspective. We smooth the classical optimal transportation problem with an entropic regularization term, and show that the resulting optimum is also a distance which can be computed through Sinkhorn's matrix scaling algorithm at a speed that is several orders of magnitude faster than that of transportation solvers. We also report improved performance on the MNIST benchmark problem over competing distances.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances

2013-06-04 · NeurIPS 2013 · Marco Cuturi

Optimal transportation distances are a fundamental family of parameterized distances for histograms. Despite their appealing theoretical properties, excellent performance in retrieval tasks and intuitive formulation, the…

Retrieval

Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration

2017-05-26 · NeurIPS 2017 12 · Jason Altschuler, Jonathan Weed, Philippe Rigollet

Computing optimal transport distances such as the earth mover's distance is a fundamental problem in machine learning, statistics, and computer vision. Despite the recent introduction of several algorithms with good empi…

BIG-bench Machine Learning

Online Sinkhorn: Optimal Transport distances from sample streams

2020-03-03 · NeurIPS 2020 12 · Arthur Mensch, Gabriel Peyré

Optimal Transport (OT) distances are now routinely used as loss functions in ML tasks. Yet, computing OT distances between arbitrary (i.e. not necessarily discrete) probability distributions remains an open problem. This…

Sinkhorn Divergences for Unbalanced Optimal Transport

2019-10-28 · Thibault Séjourné, Jean Feydy, François-Xavier Vialard, Alain Trouvé 외

Optimal transport induces the Earth Mover's (Wasserstein) distance between probability distributions, a geometric divergence that is relevant to a wide range of problems. Over the last decade, two relaxations of optimal …

Bisimulation Metrics are Optimal Transport Distances, and Can be Computed Efficiently

2024-06-06 · Sergio Calo, Anders Jonsson, Gergely Neu, Ludovic Schwartz 외

We propose a new framework for formulating optimal transport distances between Markov chains. Previously known formulations studied couplings between the entire joint distribution induced by the chains, and derived solut…