English
Related papers

Related papers: Rank-based Decomposable Losses in Machine Learning…

200 papers

The fine-tuning of deep pre-trained models has revealed compositional properties, with multiple specialized modules that can be arbitrarily composed into a single, multi-task model. However, identifying the conditions that promote…

Artificial Intelligence · Computer Science 2025-03-04 Angelo Porrello , Lorenzo Bonicelli , Pietro Buzzega , Monica Millunzi , Simone Calderara , Rita Cucchiara

We address the challenging problem of RGB image-based head pose estimation. We first reformulate head pose representation learning to constrain it to a bounded space. Head pose represented as vector projection or vector angles shows helpful…

Computer Vision and Pattern Recognition · Computer Science 2020-05-25 Donggen Dai , Wangkit Wong , Zhuojun Chen

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

Deep learning has been shown to achieve impressive results in several domains like computer vision and natural language processing. A key element of this success has been the development of new loss functions, like the popular cross-entropy…

Machine Learning · Computer Science 2019-07-19 Francesco Giannini , Giuseppe Marra , Michelangelo Diligenti , Marco Maggini , Marco Gori

Neural networks have dramatically increased our capacity to learn from large, high-dimensional datasets across innumerable disciplines. However, their decisions are not easily interpretable, their computational costs are high, and building…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Mackenzie J. Meni , Ryan T. White , Michael Mayo , Kevin Pilkiewicz

While recent continual learning methods largely alleviate the catastrophic problem on toy-sized datasets, some issues remain to be tackled to apply them to real-world problem domains. First, a continual learning model should effectively…

Machine Learning · Computer Science 2020-02-18 Jaehong Yoon , Saehoon Kim , Eunho Yang , Sung Ju Hwang

In recommendation systems, the choice of loss function is critical since a good loss may significantly improve the model performance. However, manually designing a good loss is a big challenge due to the complexity of the problem. A large…

Information Retrieval · Computer Science 2022-04-29 Zelong Li , Jianchao Ji , Yingqiang Ge , Yongfeng Zhang

Calibration is a conditional property that depends on the information retained by a predictor. We develop decomposition identities for arbitrary proper losses that make this dependence explicit. At any information level $\mathcal A$, the…

Machine Learning · Computer Science 2026-03-24 Arthur Charpentier , Agathe Fernandes Machado

We describe an algorithm to decompose rational functions from which we determine the poset of groups fixing these functions.

Number Theory · Mathematics 2008-08-21 John McKay , David Sevilla

Loss functions play an important role in training deep-network-based object detectors. The most widely used evaluation metric for object detection is Average Precision (AP), which captures the performance of localization and classification…

Computer Vision and Pattern Recognition · Computer Science 2021-12-10 Chenxin Tao , Zizhang Li , Xizhou Zhu , Gao Huang , Yong Liu , Jifeng Dai

Loss function learning is a new meta-learning paradigm that aims to automate the essential task of designing a loss function for a machine learning model. Existing techniques for loss function learning have shown promising results, often…

Machine Learning · Computer Science 2025-10-14 Christian Raymond , Qi Chen , Bing Xue , Mengjie Zhang

Imbalanced datasets are commonplace in modern machine learning problems. The presence of under-represented classes or groups with sensitive attributes results in concerns about generalization and fairness. Such concerns are further…

Machine Learning · Computer Science 2022-01-05 Mingchen Li , Xuechen Zhang , Christos Thrampoulidis , Jiasi Chen , Samet Oymak

In forming learning objectives, one oftentimes needs to aggregate a set of individual values to a single output. Such cases occur in the aggregate loss, which combines individual losses of a learning model over each training sample, and in…

Machine Learning · Computer Science 2022-04-05 Shu Hu , Yiming Ying , Xin Wang , Siwei Lyu

When it is ethical and legal to use a sensitive attribute (such as gender or race) in machine learning systems, the question remains how to do so. We show that the naive application of machine learning algorithms using sensitive features…

Machine Learning · Computer Science 2017-07-21 Cynthia Dwork , Nicole Immorlica , Adam Tauman Kalai , Max Leiserson

Despite their high accuracy, complex neural networks demand significant computational resources, posing challenges for deployment on resource constrained devices such as mobile phones and embedded systems. Compression algorithms have been…

Machine Learning · Computer Science 2025-09-23 Ali Aghababaei-Harandi , Massih-Reza Amini

We introduce two-scale loss functions for use in various gradient descent algorithms applied to classification problems via deep neural networks. This new method is generic in the sense that it can be applied to a wide range of machine…

Numerical Analysis · Mathematics 2021-09-03 Leonid Berlyand , Robert Creese , Pierre-Emmanuel Jabin

We investigate a general matrix factorization for deviance-based data losses, extending the ubiquitous singular value decomposition beyond squared error loss. While similar approaches have been explored before, our method leverages…

Machine Learning · Statistics 2023-07-04 Liang Wang , Luis Carvalho

Distributed data aggregation is an important task, allowing the decentralized determination of meaningful global properties, that can then be used to direct the execution of other applications. The resulting values result from the…

Distributed, Parallel, and Cluster Computing · Computer Science 2011-10-05 Paulo Jesus , Carlos Baquero , Paulo Sérgio Almeida

Low rank tensor decompositions are a powerful tool for learning generative models, and uniqueness results give them a significant advantage over matrix decomposition methods. However, tensors pose significant algorithmic challenges and…

Data Structures and Algorithms · Computer Science 2014-01-21 Aditya Bhaskara , Moses Charikar , Ankur Moitra , Aravindan Vijayaraghavan

Simultaneous segmentation of multiple organs from different medical imaging modalities is a crucial task as it can be utilized for computer-aided diagnosis, computer-assisted surgery, and therapy planning. Thanks to the recent advances in…

Computer Vision and Pattern Recognition · Computer Science 2021-09-16 Saeid Asgari Taghanaki , Yefeng Zheng , S. Kevin Zhou , Bogdan Georgescu , Puneet Sharma , Daguang Xu , Dorin Comaniciu , Ghassan Hamarneh
‹ Prev 1 3 4 5 6 7 10 Next ›