English
Related papers

Related papers: Sample Complexity of Sinkhorn divergences

200 papers

We analyze the sample complexity of full-batch Gradient Descent (GD) in the setup of non-smooth Stochastic Convex Optimization. We show that the generalization error of GD, with common choice of hyper-parameters, can be $\tilde \Theta(d/m +…

Machine Learning · Computer Science 2024-04-12 Roi Livni

Optimal Transport is a popular distance metric for measuring similarity between distributions. Exact algorithms for computing Optimal Transport can be slow, which has motivated the development of approximate numerical solvers (e.g. Sinkhorn…

Machine Learning · Computer Science 2022-03-09 Nathaniel Lahn , Sharath Raghvendra , Kaiyi Zhang

We propose a novel approach based on optimal transport (OT) for tackling the problem of highly mixed data in blind hyperspectral unmixing. Our method constrains the distribution of the estimated abundance matrix to resemble a targeted…

Image and Video Processing · Electrical Eng. & Systems 2025-09-26 D. Doutsas , B. Figliuzzi

The saddlepoint approximation gives an approximation to the density of a random variable in terms of its moment generating function. When the underlying random variable is itself the sum of $n$ unobserved i.i.d. terms, the basic classical…

Statistics Theory · Mathematics 2022-01-25 Jesse Goodman

We define a novel class of distances between statistical multivariate distributions by modeling an optimal transport problem on their marginals with respect to a ground distance defined on their conditionals. These new distances are metrics…

Machine Learning · Computer Science 2020-11-03 Frank Nielsen , Ke Sun

We study Sinkhorn's algorithm for solving the entropically regularized optimal transport problem. Its iterate $\pi_{t}$ is shown to satisfy $H(\pi_{t}|\pi_{*})+H(\pi_{*}|\pi_{t})=O(t^{-1})$ where $H$ denotes relative entropy and $\pi_{*}$…

Optimization and Control · Mathematics 2025-04-08 Promit Ghosal , Marcel Nutz

The sharpest known high probability generalization bounds for uniformly stable algorithms (Feldman, Vondr\'{a}k, 2018, 2019), (Bousquet, Klochkov, Zhivotovskiy, 2020) contain a generally inevitable sampling error term of order…

Machine Learning · Computer Science 2021-11-19 Yegor Klochkov , Nikita Zhivotovskiy

In 2013, Cuturi [Cut13] introduced the Sinkhorn algorithm for matrix scaling as a method to compute solutions to regularized optimal transport problems. In this paper, aiming at a better convergence rate for a high accuracy solution, we…

Data Structures and Algorithms · Computer Science 2023-04-06 Jingbang Chen , Li Chen , Yang P. Liu , Richard Peng , Arvind Ramaswami

We study the multi-marginal partial optimal transport (POT) problem between $m$ discrete (unbalanced) measures with at most $n$ supports. We first prove that we can obtain two equivalence forms of the multimarginal POT problem in terms of…

Machine Learning · Statistics 2022-02-25 Khang Le , Huy Nguyen , Tung Pham , Nhat Ho

In this paper, we propose a new framework named Communication Optimal Transport (CommOT) for computing the rate distortion (RD) function. This work is motivated by observing the fact that the transition law and the relative entropy in…

Information Theory · Computer Science 2022-12-21 Shitong Wu , Wenhao Ye , Hao Wu , Huihui Wu , Wenyi Zhang , Bo Bai

We study the classical NP-hard problems of finding maximum-size subsets from given sets of $k$ terminal pairs that can be routed via edge-disjoint paths (MaxEDP) or node-disjoint paths (MaxNDP) in a given graph. The approximability of…

Data Structures and Algorithms · Computer Science 2016-05-23 Krzysztof Fleszar , Matthias Mnich , Joachim Spoerhase

Sinkhorn's algorithm is a method of choice to solve large-scale optimal transport (OT) problems. In this context, it involves an inverse temperature parameter $\beta$ that determines the speed-accuracy trade-off. To improve this trade-off,…

Machine Learning · Computer Science 2024-08-22 Lénaïc Chizat

We rigorously quantify the improvement in the sample complexity of variational divergence estimations for group-invariant distributions. In the cases of the Wasserstein-1 metric and the Lipschitz-regularized $\alpha$-divergences, the…

Statistics Theory · Mathematics 2024-11-26 Ziyu Chen , Markos A. Katsoulakis , Luc Rey-Bellet , Wei Zhu

Despite being highly over-parametrized, and having the ability to fully interpolate the training data, deep networks are known to generalize well to unseen data. It is now understood that part of the reason for this is that the training…

Machine Learning · Computer Science 2023-02-21 Danil Akhtiamov , Babak Hassibi

We consider an optimal transport problem on the unit simplex whose solutions are given by gradients of exponentially concave functions and prove two main results. First, we show that the optimal transport is the large deviation limit of a…

Probability · Mathematics 2020-07-07 Soumik Pal , Ting-Kam Leonard Wong

Sinkhorn algorithm is the de-facto standard approximation algorithm for optimal transport, which has been applied to a variety of applications, including image processing and natural language processing. In theory, the proof of its…

Data Structures and Algorithms · Computer Science 2025-01-14 Kazuki Watanabe , Noboru Isobe

Decentralized stochastic gradient descent (D-SGD) is an efficient method for large-scale distributed learning. Existing generalization studies mainly address expected results, achieving rates limited to $\mathcal{O}\left(\frac{1}{\delta…

Machine Learning · Computer Science 2026-05-12 Jiahuan Wang , Ping Luo , Ziqing Wen , Dongsheng Li , Tao Sun

Distributionally robust optimization (DRO) is a powerful technique to train robust models against data distribution shift. This paper aims to solve regularized nonconvex DRO problems, where the uncertainty set is modeled by a so-called…

Optimization and Control · Mathematics 2025-06-30 Yufeng Yang , Yi Zhou , Zhaosong Lu

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, their computation…

Machine Learning · Statistics 2014-03-25 Marco Cuturi

Multimarginal optimal transport (MOT) is a powerful framework for modeling interactions between multiple distributions, yet its applicability is bottlenecked by a high computational overhead. Entropic regularization provides computational…

Machine Learning · Computer Science 2025-06-03 Dor Tsur , Ziv Goldfeld , Kristjan Greenewald , Haim Permuter