English
Related papers

Related papers: Learning Classifiers with Fenchel-Young Losses: Ge…

200 papers

In this paper, we investigate the partition inequality, joint convexity, and Pinsker's inequality, for a divergence that generalizes the Tsallis Relative Entropy and Kullback-Leibler divergence. The generalized divergence is defined in…

Information Theory · Computer Science 2020-04-27 Rui F. Vigelis , Luiza H. F. de Andrade , Charles C. Cavalcante

We consider the setting of prediction with expert advice; a learner makes predictions by aggregating those of a group of experts. Under this setting, and for the right choice of loss function and "mixing" algorithm, it is possible for the…

Machine Learning · Computer Science 2018-11-01 Zakaria Mhammedi , Robert C. Williamson

Prior works have found it beneficial to combine provably noise-robust loss functions e.g., mean absolute error (MAE) with standard categorical loss function e.g. cross entropy (CE) to improve their learnability. Here, we propose to use…

Machine Learning · Computer Science 2021-11-01 Erik Englesson , Hossein Azizpour

Generalization error bounds are essential for comprehending how well machine learning models work. In this work, we suggest a novel method, i.e., the Auxiliary Distribution Method, that leads to new upper bounds on expected generalization…

Machine Learning · Computer Science 2024-04-18 Gholamali Aminian , Saeed Masiha , Laura Toni , Miguel R. D. Rodrigues

The classical concept of Fenchel conjugation is tailored to extended real-valued functions defined on linear spaces. In this paper we generalize this concept to functions defined on arbitrary sets that do not necessarily bear any structure…

Functional Analysis · Mathematics 2024-09-11 Anton Schiela , Roland Herzog , Ronny Bergmann

Cross-entropy loss and focal loss are the most common choices when training deep neural networks for classification problems. Generally speaking, however, a good loss function can take on much more flexible forms, and should be tailored for…

Computer Vision and Pattern Recognition · Computer Science 2022-05-12 Zhaoqi Leng , Mingxing Tan , Chenxi Liu , Ekin Dogus Cubuk , Xiaojie Shi , Shuyang Cheng , Dragomir Anguelov

The standard margin-based structured prediction commonly uses a maximum loss over all possible structured outputs. The large-margin formulation including latent variables not only results in a non-convex formulation but also increases the…

Machine Learning · Computer Science 2019-06-25 Kevin Bello , Jean Honorio

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

Standard uniform convergence results bound the generalization gap of the expected loss over a hypothesis class. The emergence of risk-sensitive learning requires generalization guarantees for functionals of the loss distribution beyond the…

Machine Learning · Statistics 2022-06-29 Liu Leqi , Audrey Huang , Zachary C. Lipton , Kamyar Azizzadenesheli

We present a generalization of the Cauchy/Lorentzian, Geman-McClure, Welsch/Leclerc, generalized Charbonnier, Charbonnier/pseudo-Huber/L1-L2, and L2 loss functions. By introducing robustness as a continuous parameter, our loss function…

Computer Vision and Pattern Recognition · Computer Science 2019-04-08 Jonathan T. Barron

Most classification models can be considered as the process of matching templates. However, when intra-class uncertainty/variability is not considered, especially for datasets containing unbalanced classes, this may lead to classification…

Computer Vision and Pattern Recognition · Computer Science 2021-04-13 He Zhu , Shan Yu

This paper studies the generalization properties of a recently proposed kernel method, the Random Feature models with Learnable Activation Functions (RFLAF). By applying a data-dependent sampling scheme for generating features, we provide…

Machine Learning · Computer Science 2025-10-20 Zailin Ma , Jiansheng Yang , Yaodong Yang

This article proposes a new two-parameter generalized entropy, which can be reduced to the Tsallis and the Shannon entropy for specific values of its parameters. We develop a number of information-theoretic properties of this generalized…

Mathematical Physics · Physics 2024-05-02 Supriyo Dutta , Shigeru Furuichi , Partha Guha

Federated Learning (FL) enables collaborative model training across distributed devices while preserving data privacy. Nonetheless, the heterogeneity of edge devices often leads to inconsistent performance of the globally trained models,…

Machine Learning · Computer Science 2025-05-13 Lin Wang , Zhichao Wang , Ye Shi , Sai Praneeth Karimireddy , Xiaoying Tang

In this article, we study rates of convergence of the generalization error of multi-class margin classifiers. In particular, we develop an upper bound theory quantifying the generalization error of various large margin classifiers. The…

Statistics Theory · Mathematics 2011-11-10 Xiaotong Shen , Lifeng Wang

Nearly all practical neural models for classification are trained using cross-entropy loss. Yet this ubiquitous choice is supported by little theoretical or empirical evidence. Recent work (Hui & Belkin, 2020) suggests that training using…

Machine Learning · Computer Science 2023-02-09 Like Hui , Mikhail Belkin , Stephen Wright

Deep Metric Learning (DML) learns a non-linear semantic embedding from input data that brings similar pairs together while keeping dissimilar data away from each other. To this end, many different methods are proposed in the last decade…

Computer Vision and Pattern Recognition · Computer Science 2023-01-02 Davood Zabihzadeh , Zahraa Alitbi , Seyed Jalaleddin Mousavirad

In this paper we remark that Shannon entropy can be expressed as a function of the self-information (i.e. the logarithm) and the inverse of the Lambert $W$ function. It means that we consider that Shannon entropy has the trace form: $-k…

Statistical Mechanics · Physics 2019-07-05 Laurent Truffet

One of the central challenges in modern machine learning is understanding how neural networks generalize knowledge learned from training data to unseen test data. While numerous empirical techniques have been proposed to improve…

Machine Learning · Computer Science 2025-04-18 Entao Yang , Xiaotian Zhang , Yue Shang , Ge Zhang

Cross-entropy loss is the standard metric used to train classification models in deep learning and gradient boosting. It is well-known that this loss function fails to account for similarities between the different values of the target. We…

Machine Learning · Statistics 2022-06-16 Brian Lucena