English
Related papers

Related papers: Loss Functions and Operators Generated by f-Diverg…

200 papers

Bayesian neural networks (BNNs) are state-of-the-art machine learning methods that can naturally regularize and systematically quantify uncertainties using their stochastic parameters. Kullback-Leibler (KL) divergence-based variational…

Machine Learning · Computer Science 2024-12-10 Ponkrshnan Thiagarajan , Susanta Ghosh

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

Diffusion models have emerged as powerful generative models, inspiring extensive research into their underlying mechanisms. One of the key questions in this area is the loss functions these models shall train with. Multiple formulations…

Machine Learning · Computer Science 2025-07-03 Dibyanshu Kumar , Philipp Vaeth , Magda Gregorová

In computer vision, it is often observed that formulating regression problems as a classification task often yields better performance. We investigate this curious phenomenon and provide a derivation to show that classification, with the…

Computer Vision and Pattern Recognition · Computer Science 2023-03-01 Shihao Zhang , Linlin Yang , Michael Bi Mi , Xiaoxu Zheng , Angela Yao

We present a new loss function called Distribution-Balanced Loss for the multi-label recognition problems that exhibit long-tailed class distributions. Compared to conventional single-label classification problem, multi-label recognition…

Computer Vision and Pattern Recognition · Computer Science 2021-12-07 Tong Wu , Qingqiu Huang , Ziwei Liu , Yu Wang , Dahua Lin

We study loss functions that measure the accuracy of a prediction based on multiple data points simultaneously. To our knowledge, such loss functions have not been studied before in the area of property elicitation or in machine learning…

Machine Learning · Computer Science 2017-06-06 Sebastian Casalaina-Martin , Rafael Frongillo , Tom Morgan , Bo Waggoner

We define a class of divergences to measure differences between probability density functions in one-dimensional sample space. The construction is based on the convex function with the Jacobi operator of mapping function that pushforwards…

Statistics Theory · Mathematics 2025-04-24 Wuchen Li

Many NLP tasks such as tagging and machine reading comprehension are faced with the severe data imbalance issue: negative examples significantly outnumber positive examples, and the huge number of background examples (or easy-negative…

Computation and Language · Computer Science 2020-09-01 Xiaoya Li , Xiaofei Sun , Yuxian Meng , Junjun Liang , Fei Wu , Jiwei Li

Variational inference with {\alpha}-divergences has been widely used in modern probabilistic machine learning. Compared to Kullback-Leibler (KL) divergence, a major advantage of using {\alpha}-divergences (with positive {\alpha} values) is…

Machine Learning · Computer Science 2019-09-10 Dilin Wang , Hao Liu , Qiang Liu

Recent works have studied implicit biases in deep learning, especially the behavior of last-layer features and classifier weights. However, they usually need to simplify the intermediate dynamics under gradient flow or gradient descent due…

Machine Learning · Computer Science 2023-12-14 Xiong Zhou , Xianming Liu , Hanzhang Wang , Deming Zhai , Junjun Jiang , Xiangyang Ji

Federated multi-task learning (FMTL) seeks to collaboratively train customized models for users with different tasks while preserving data privacy. Most existing approaches assume model congruity (i.e., the use of fully or partially…

Machine Learning · Computer Science 2026-02-03 Mehdi Setayesh , Mahdi Beitollahi , Yasser H. Khalil , Hongliang Li

A new loss function is proposed for neural networks on classification tasks which extends the hinge loss by assigning gradients to its critical points. We will show that for a linear classifier on linearly separable data with fixed step…

Machine Learning · Computer Science 2020-06-26 Justin Lizama

Many important computer vision tasks are naturally formulated to have a non-differentiable objective. Therefore, the standard, dominant training procedure of a neural network is not applicable since back-propagation requires the gradients…

Computer Vision and Pattern Recognition · Computer Science 2023-05-04 Yash Patel

Soft targets combined with the cross-entropy loss have shown to improve generalization performance of deep neural networks on supervised classification tasks. The standard cross-entropy loss however assumes data to be categorically…

Machine Learning · Computer Science 2024-07-16 Johannes Hugger , Virginie Uhlmann

With recent legislation on the right to be forgotten, machine unlearning has emerged as a crucial research area. It facilitates the removal of a user's data from federated trained machine learning models without the necessity for retraining…

Machine Learning · Computer Science 2024-04-24 Houzhe Wang , Xiaojie Zhu , Chi Chen , Paulo Esteves-Veríssimo

Recent work has attempted to directly approximate the `function-space' or predictive posterior distribution of Bayesian models, without approximating the posterior distribution over the parameters. This is appealing in e.g. Bayesian neural…

Machine Learning · Statistics 2020-11-19 David R. Burt , Sebastian W. Ober , Adrià Garriga-Alonso , Mark van der Wilk

Miscalibration - a mismatch between a model's confidence and its correctness - of Deep Neural Networks (DNNs) makes their predictions hard to rely on. Ideally, we want networks to be accurate, calibrated and confident. We show that, as…

Machine Learning · Computer Science 2020-10-27 Jishnu Mukhoti , Viveka Kulharia , Amartya Sanyal , Stuart Golodetz , Philip H. S. Torr , Puneet K. Dokania

Learning to generate a task-aware base learner proves a promising direction to deal with few-shot learning (FSL) problem. Existing methods mainly focus on generating an embedding model utilized with a fixed metric (eg, cosine distance) for…

Computer Vision and Pattern Recognition · Computer Science 2020-12-04 Lei Zhang , Fei Zhou , Wei Wei , Yanning Zhang

Deep learning has become the method of choice in many application domains of machine learning in recent years, especially for multi-class classification tasks. The most common loss function used in this context is the cross-entropy loss,…

Machine Learning · Computer Science 2017-04-21 Yehezkel S. Resheff , Amit Mandelbaum , Daphna Weinshall

We examine gradient descent on unregularized logistic regression problems, with homogeneous linear predictors on linearly separable datasets. We show the predictor converges to the direction of the max-margin (hard margin SVM) solution. The…

Machine Learning · Statistics 2024-10-29 Daniel Soudry , Elad Hoffer , Mor Shpigel Nacson , Suriya Gunasekar , Nathan Srebro
‹ Prev 1 8 9 10 Next ›