English
Related papers

Related papers: Hard Negative Sampling via Regularized Optimal Tra…

200 papers

We consider the fundamental problem of sampling the optimal transport coupling between given source and target distributions. In certain cases, the optimal transport plan takes the form of a one-to-one mapping from the source support to the…

Machine Learning · Computer Science 2025-10-28 Mara Daniels , Tyler Maunu , Paul Hand

Optimal transport (OT) compares probability distributions by computing a meaningful alignment between their samples. CO-optimal transport (COOT) takes this comparison further by inferring an alignment between features as well. While this…

Noise contrastive learning is a popular technique for unsupervised representation learning. In this approach, a representation is obtained via reduction to supervised learning, where given a notion of semantic similarity, the learner tries…

Machine Learning · Computer Science 2021-06-21 Jordan T. Ash , Surbhi Goel , Akshay Krishnamurthy , Dipendra Misra

Optimal Transport (OT) offers a powerful framework for finding correspondences between distributions and addressing matching and alignment problems in various areas of computer vision, including shape analysis, image generation, and…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Xinran Liu , Elaheh Akbari , Rocio Diaz Martin , Navid NaderiAlizadeh , Soheil Kolouri

This paper investigates, from information theoretic grounds, a learning problem based on the principle that any regularity in a given dataset can be exploited to extract compact features from data, i.e., using fewer bits than needed to…

Machine Learning · Statistics 2018-11-14 Matías Vera , Leonardo Rey Vega , Pablo Piantanida

We consider statistical learning problems in which data are observed as a set of probability measures. Optimal transport (OT) is a popular tool to compare and manipulate such objects, but its computational cost becomes prohibitive when the…

Machine Learning · Statistics 2026-03-24 Erell Gachon , Elsa Cazelles , Jérémie Bigot

In machine learning and computer graphics, a fundamental task is the approximation of a probability density function through a well-dispersed collection of samples. Providing a formal metric for measuring the distance between probability…

Graphics · Computer Science 2024-02-28 Baptiste Genest , Nicolas Courty , David Coeurjolly

Recently, linear regression models incorporating an optimal transport (OT) loss have been explored for applications such as supervised unmixing of spectra, music transcription, and mass spectrometry. However, these task-specific approaches…

Inverse Reinforcement Learning (IRL) aims to recover a reward function from expert demonstrations. Recently, Optimal Transport (OT) methods have been successfully deployed to align trajectories and infer rewards. While OT-based methods have…

Machine Learning · Computer Science 2025-06-10 Zixuan Dong , Yumi Omori , Keith Ross

This paper addresses the limitations of standard uncertainty models, e.g., robust (norm-bounded) and stochastic (one fixed distribution, e.g., Gaussian), and proposes to model uncertainty via Optimal Transport (OT) ambiguity sets. These…

Optimization and Control · Mathematics 2023-09-08 Liviu Aolaritei , Nicolas Lanzetti , Hongruyu Chen , Florian Dörfler

In this paper, we propose to solve a regularized distributionally robust learning problem in the decentralized setting, taking into account the data distribution shift. By adding a Kullback-Liebler regularization function to the robust…

Machine Learning · Computer Science 2022-09-13 Chaouki Ben Issaid , Anis Elgabli , Mehdi Bennis

Optimal Transport (OT) distances such as Wasserstein have been used in several areas such as GANs and domain adaptation. OT, however, is very sensitive to outliers (samples with large noise) in the data since in its objective function,…

Machine Learning · Computer Science 2020-10-13 Yogesh Balaji , Rama Chellappa , Soheil Feizi

Given samples from two joint distributions, we consider the problem of Optimal Transportation (OT) between them when conditioned on a common variable. We focus on the general setting where the conditioned variable may be continuous, and the…

Machine Learning · Computer Science 2024-06-12 Piyushi Manupriya , Rachit Keerti Das , Sayantan Biswas , Saketha Nath Jagarlapudi

Optimal transport (OT) is a powerful geometric and probabilistic tool for finding correspondences and measuring similarity between two distributions. Yet, its original formulation relies on the existence of a cost function between the…

Machine Learning · Statistics 2020-11-09 Ievgen Redko , Titouan Vayer , Rémi Flamary , Nicolas Courty

We study stability and sample complexity properties of divergence regularized optimal transport (DOT). First, we obtain quantitative stability results for optimizers of DOT measured in Wasserstein distance, which are applicable to a wide…

Optimization and Control · Mathematics 2024-01-17 Erhan Bayraktar , Stephan Eckstein , Xin Zhang

Self-supervised learning has revolutionized representation learning by eliminating the need for labeled data. Contrastive learning methods, such as SimCLR, maximize the agreement between augmented views of an image but lack explicit…

Machine Learning · Computer Science 2025-02-18 M. Hadi Sepanj , Paul Fiegth

For probability measures on countable spaces we derive distributional limits for empirical entropic optimal transport quantities. More precisely, we show that the empirical optimal transport plan weakly converges to a centered Gaussian…

Probability · Mathematics 2022-12-27 Shayan Hundrieser , Marcel Klatt , Axel Munk

Variational Auto-Encoders enforce their learned intermediate latent-space data distribution to be a simple distribution, such as an isotropic Gaussian. However, this causes the posterior collapse problem and loses manifold structure which…

Machine Learning · Computer Science 2018-09-18 Huidong Liu , Yang Guo , Na Lei , Zhixin Shu , Shing-Tung Yau , Dimitris Samaras , Xianfeng Gu

Contrastive representation learning has been recently proved to be very efficient for self-supervised training. These methods have been successfully used to train encoders which perform comparably to supervised training on downstream…

Machine Learning · Computer Science 2020-12-03 Ibrahim Merad , Yiyang Yu , Emmanuel Bacry , Stéphane Gaïffas

Recent investigations in noise contrastive estimation suggest, both empirically as well as theoretically, that while having more "negative samples" in the contrastive loss improves downstream classification performance initially, beyond a…

Machine Learning · Computer Science 2022-06-24 Pranjal Awasthi , Nishanth Dikkala , Pritish Kamath
‹ Prev 1 4 5 6 7 8 10 Next ›