Recent Advances in Optimal Transport for Machine Learning

• URL: http://arxiv.org/abs/2306.16156v2
• Date: Wed, 21 Aug 2024 08:44:44 GMT
• Title: Recent Advances in Optimal Transport for Machine Learning
• Authors: Eduardo Fernandes Montesuma, Fred Ngolè Mboula, Antoine Souloumiac,
• Abstract summary: We explore contributions of Optimal Transport for Machine Learning over the period 2012 -- 2023. We focus on four sub-fields of Machine Learning: supervised, unsupervised, transfer and reinforcement learning. We highlight the recent development in computational Optimal Transport and its extensions.
• Score: 5.492296610282042
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, Optimal Transport has been proposed as a probabilistic framework in Machine Learning for comparing and manipulating probability distributions. This is rooted in its rich history and theory, and has offered new solutions to different problems in machine learning, such as generative modeling and transfer learning. In this survey we explore contributions of Optimal Transport for Machine Learning over the period 2012 -- 2023, focusing on four sub-fields of Machine Learning: supervised, unsupervised, transfer and reinforcement learning. We further highlight the recent development in computational Optimal Transport and its extensions, such as partial, unbalanced, Gromov and Neural Optimal Transport, and its interplay with Machine Learning practice.

Related papers

• Computing low-thrust transfers in the asteroid belt, a comparison between astrodynamical manipulations and a machine learning approach [4.868863044142366]
  Low-thrust trajectories play a crucial role in optimizing scientific output and cost efficiency in asteroid belt missions. We propose new analytical approximations and compare their accuracy and performance to machine learning methods. We build a dataset of about 3 million transfers, found by solving the time and fuel optimal control problems.
  arXiv  Detail & Related papers  (2024-05-29T09:20:54Z)
• Advantages of Machine Learning in Bus Transport Analysis [0.0]
  We utilize supervised machine learning algorithms to analyze the factors that contribute to the punctuality of Tehran BRT bus system. We construct accurate models capable of predicting whether a bus route will meet the prescribed standards for on-time performance on any given day.
  arXiv  Detail & Related papers  (2023-10-16T13:02:43Z)
• Feasibility of Transfer Learning: A Mathematical Framework [4.530876736231948]
  It begins by establishing the necessary mathematical concepts and constructing a mathematical framework for transfer learning. It then identifies and formulates the three-step transfer learning procedure as an optimization problem, allowing for the resolution of the feasibility issue.
  arXiv  Detail & Related papers  (2023-05-22T12:44:38Z)
• Scalable Optimal Transport Methods in Machine Learning: A Contemporary Survey [15.500897098518989]
  This paper is about where and how optimal transport is used in machine learning. We first explain the optimal transport background and introduce different flavors (i.e., mathematical formulations), properties, and notable applications. We then address the fundamental question of how to scale optimal transport to cope with the current demands of big and high dimensional data.
  arXiv  Detail & Related papers  (2023-05-08T22:43:16Z)
• Vision Paper: Causal Inference for Interpretable and Robust Machine Learning in Mobility Analysis [71.2468615993246]
  Building intelligent transportation systems requires an intricate combination of artificial intelligence and mobility analysis. The past few years have seen rapid development in transportation applications using advanced deep neural networks. This vision paper emphasizes research challenges in deep learning-based mobility analysis that require interpretability and robustness.
  arXiv  Detail & Related papers  (2022-10-18T17:28:58Z)
• OMLT: Optimization & Machine Learning Toolkit [54.58348769621782]
  The optimization and machine learning toolkit (OMLT) is an open-source software package incorporating neural network and gradient-boosted tree surrogate models. We discuss the advances in optimization technology that made OMLT possible and show how OMLT seamlessly integrates with the algebraic modeling language Pyomo.
  arXiv  Detail & Related papers  (2022-02-04T22:23:45Z)
• Estimating the Robustness of Public Transport Systems Using Machine Learning [62.997667081978825]
  Planning public transport systems is a highly complex process involving many steps. Integrating robustness from a passenger's point of view makes the task even more challenging. In this paper, we explore a new way of such a scenario-based robustness approximation by using methods from machine learning.
  arXiv  Detail & Related papers  (2021-06-10T05:52:56Z)
• Transferable Deep Reinforcement Learning Framework for Autonomous Vehicles with Joint Radar-Data Communications [69.24726496448713]
  We propose an intelligent optimization framework based on the Markov Decision Process (MDP) to help the AV make optimal decisions. We then develop an effective learning algorithm leveraging recent advances of deep reinforcement learning techniques to find the optimal policy for the AV. We show that the proposed transferable deep reinforcement learning framework reduces the obstacle miss detection probability by the AV up to 67% compared to other conventional deep reinforcement learning approaches.
  arXiv  Detail & Related papers  (2021-05-28T08:45:37Z)
• Measuring and modeling the motor system with machine learning [117.44028458220427]
  The utility of machine learning in understanding the motor system is promising a revolution in how to collect, measure, and analyze data. We discuss the growing use of machine learning: from pose estimation, kinematic analyses, dimensionality reduction, and closed-loop feedback, to its use in understanding neural correlates and untangling sensorimotor systems.
  arXiv  Detail & Related papers  (2021-03-22T12:42:16Z)
• First-order Optimization for Superquantile-based Supervised Learning [0.0]
  We propose a first-order optimization algorithm to minimize a superquantile-based learning objective. The proposed algorithm is based on smoothing the superquantile function by infimal convolution.
  arXiv  Detail & Related papers  (2020-09-30T11:43:45Z)
• A Survey on Large-scale Machine Learning [67.6997613600942]
  Machine learning can provide deep insights into data, allowing machines to make high-quality predictions. Most sophisticated machine learning approaches suffer from huge time costs when operating on large-scale data. Large-scale Machine Learning aims to learn patterns from big data with comparable performance efficiently.
  arXiv  Detail & Related papers  (2020-08-10T06:07:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.