paper-with-me

Papers

Sinkhorn algorithms and linear programming solvers for optimal partial transport problems

2024-07-09 · Yikun Bai

In this note, we generalize the classical optimal partial transport (OPT) problem by modifying the mass destruction/creation term to function-based terms, introducing what we term ``generalized optimal partial transport'' problems. We then discuss the dual formulation of these problems and the associated Sinkhorn solver. Finally, we explore how these new OPT problems relate to classical optimal transport (OT) problems and introduce a linear programming solver tailored for these generalized scenarios.

📄 PDF Abstract BibTeX arXiv:2407.06481

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

OPT OPT is a suite of decoder-only pre-trained transformers ranging from 125M to 175B parameters. The model uses an AdamW optimizer and weight decay of 0.1. It follows a linear…

Similar Papers 제목 키워드 기반

Quantized Wasserstein Procrustes Alignment of Word Embedding Spaces

2022-12-05 · AMTA 2022 9 · Prince O Aboagye, Yan Zheng, Michael Yeh, Junpeng Wang 외

Optimal Transport (OT) provides a useful geometric framework to estimate the permutation matrix under unsupervised cross-lingual word embedding (CLWE) models that pose the alignment task as a Wasserstein-Procrustes probl…

Bilingual Lexicon InductionQuantization

On the Complexity of Approximating Multimarginal Optimal Transport

2019-09-30 · Tianyi Lin, Nhat Ho, Marco Cuturi, Michael. I. Jordan

We study the complexity of approximating the multimarginal optimal transport (MOT) distance, a generalization of the classical optimal transport distance, considered here between $m$ discrete probability distributions su…

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

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 …

FlashSinkhorn: IO-Aware Entropic Optimal Transport on GPU

2026-02-03 · Felix X. -F. Ye, Xingjie Li, An Yu, Ming-Ching Chang 외 arxiv

Entropic optimal transport (EOT) via Sinkhorn iterations is widely used in modern machine learning, yet GPU solvers remain inefficient at scale. Tensorized implementations suffer quadratic HBM traffic from dense $n\times…