English
Related papers

Related papers: An Optimal Transport View on Generalization

200 papers

How to train deep neural networks (DNNs) to generalize well is a central concern in deep learning, especially for severely overparameterized networks nowadays. In this paper, we propose an effective method to improve the model…

Machine Learning · Computer Science 2022-06-28 Yang Zhao , Hao Zhang , Xiuyuan Hu

Recent studies showed that the generalization of neural networks is correlated with the sharpness of the loss landscape, and flat minima suggests a better generalization ability than sharp minima. In this paper, we propose a novel method…

Machine Learning · Computer Science 2024-05-24 Yuyan Zhou , Ye Li , Lei Feng , Sheng-Jun Huang

We study the continuity property of the generalized entropy as a function of the underlying probability distribution, defined with an action space and a loss function, and use this property to answer the basic questions in statistical…

Machine Learning · Computer Science 2022-01-04 Aolin Xu

The distance and divergence of the probability measures play a central role in statistics, machine learning, and many other related fields. The Wasserstein distance has received much attention in recent years because of its distinctions…

Statistics Theory · Mathematics 2021-03-11 Qijun Tong , Kei Kobayashi

We derive upper bounds on the generalization error of a learning algorithm in terms of the mutual information between its input and output. The bounds provide an information-theoretic understanding of generalization in learning problems,…

Machine Learning · Computer Science 2017-11-07 Aolin Xu , Maxim Raginsky

It is often desired that ordinal regression models yield unimodal predictions. However, in many recent works this characteristic is either absent, or implemented using soft targets, which do not guarantee unimodal outputs at inference. In…

Machine Learning · Statistics 2021-11-19 Uri Shaham , Igal Zaidman , Jonathan Svirsky

The lack of mathematical tractability of Deep Neural Networks (DNNs) has hindered progress towards having a unified convergence analysis of training algorithms, in the general setting. We propose a unified optimization framework for…

Machine Learning · Computer Science 2018-05-24 Hadi Ghauch , Hossein Shokri-Ghadikolaei , Carlo Fischione , Mikael Skoglund

Emotions are an essential part of human behavior that can impact thinking, decision-making, and communication skills. Thus, the ability to accurately monitor and identify emotions can be useful in many human-centered applications such as…

Machine Learning · Computer Science 2023-08-22 Nibraas Khan , Mahrukh Tauseef , Ritam Ghosh , Nilanjan Sarkar

The Wasserstein distance, rooted in optimal transport (OT) theory, is a popular discrepancy measure between probability distributions with various applications to statistics and machine learning. Despite their rich structure and…

Machine Learning · Statistics 2023-03-02 Sloan Nietert , Rachel Cummings , Ziv Goldfeld

Hypergraph neural networks have been promising tools for handling learning tasks involving higher-order data, with notable applications in web graphs, such as modeling multi-way hyperlink structures and complex user interactions. Yet, their…

Machine Learning · Computer Science 2025-01-28 Yifan Wang , Gonzalo R. Arce , Guangmo Tong

In this paper, we show that, in vector-to-vector regression utilizing deep neural networks (DNNs), a generalized loss of mean absolute error (MAE) between the predicted and expected feature vectors is upper bounded by the sum of an…

Machine Learning · Computer Science 2020-08-13 Jun Qi , Jun Du , Sabato Marco Siniscalchi , Xiaoli Ma , Chin-Hui Lee

In many machine learning applications, it is necessary to meaningfully aggregate, through alignment, different but related datasets. Optimal transport (OT)-based approaches pose alignment as a divergence minimization problem: the aim is to…

Machine Learning · Statistics 2019-11-05 John Lee , Max Dabagia , Eva L. Dyer , Christopher J. Rozell

Deep learning achieves remarkable generalization capability with overwhelming number of model parameters. Theoretical understanding of deep learning generalization receives recent attention yet remains not fully explored. This paper…

Machine Learning · Computer Science 2017-11-22 Guanhua Zheng , Jitao Sang , Changsheng Xu

The ability to compare two degenerate probability distributions (i.e. two probability distributions supported on two distinct low-dimensional manifolds living in a much higher-dimensional space) is a crucial problem arising in the…

Machine Learning · Statistics 2017-10-23 Aude Genevay , Gabriel Peyré , Marco Cuturi

Entropic optimal transport (OT) and the Sinkhorn algorithm have made it practical for machine learning practitioners to perform the fundamental task of calculating transport distance between statistical distributions. In this work, we focus…

Optimization and Control · Mathematics 2024-03-11 Xun Tang , Holakou Rahmanian , Michael Shavlovsky , Kiran Koshy Thekumparampil , Tesi Xiao , Lexing Ying

We carry out an information-theoretical analysis of a two-layer neural network trained from input-output pairs generated by a teacher network with matching architecture, in overparametrized regimes. Our results come in the form of bounds…

Machine Learning · Computer Science 2023-07-13 Francesco Camilli , Daria Tieplova , Jean Barbier

Existing generalization theories of supervised learning typically take a holistic approach and provide bounds for the expected generalization over the whole data distribution, which implicitly assumes that the model generalizes similarly…

Machine Learning · Computer Science 2024-01-08 Firas Laakom , Yuheng Bu , Moncef Gabbouj

We present a novel neural-networks-based algorithm to compute optimal transport maps and plans for strong and weak transport costs. To justify the usage of neural networks, we prove that they are universal approximators of transport plans…

Machine Learning · Computer Science 2023-03-02 Alexander Korotin , Daniil Selikhanovych , Evgeny Burnaev

Fitting a function by using linear combinations of a large number $N$ of `simple' components is one of the most fruitful ideas in statistical learning. This idea lies at the core of a variety of methods, from two-layer neural networks to…

Statistics Theory · Mathematics 2019-08-20 Adel Javanmard , Marco Mondelli , Andrea Montanari

We study the estimation problem of distribution-on-distribution regression, where both predictors and responses are probability measures. Existing approaches typically rely on a global optimal transport map or tangent-space linearization,…

Machine Learning · Statistics 2025-11-17 Inga Girshfeld , Xiaohui Chen