English
Related papers

Related papers: Cut your Losses with Squentropy

200 papers

In neural networks, the loss function represents the core of the learning process that leads the optimizer to an approximation of the optimal convergence error. Convolutional neural networks (CNN) use the loss function as a supervisory…

Computer Vision and Pattern Recognition · Computer Science 2020-09-30 Riccardo La Grassa , Ignazio Gallo , Nicola Landro

In deep neural network, the cross-entropy loss function is commonly used for classification. Minimizing cross-entropy is equivalent to maximizing likelihood under assumptions of uniform feature and class distributions. It belongs to…

Machine Learning · Computer Science 2018-05-01 Donglai Zhu , Hengshuai Yao , Bei Jiang , Peng Yu

We propose a novel scaling law for general-purpose decoder-only language models (LMs) trained on multilingual data, tackling the problem of balancing languages during multilingual pretraining. A primary challenge in studying multilingual…

Computation and Language · Computer Science 2024-12-05 Yifei He , Alon Benhaim , Barun Patra , Praneetha Vaddamanu , Sanchit Ahuja , Parul Chopra , Vishrav Chaudhary , Han Zhao , Xia Song

The amount of manually labeled data is limited in medical applications, so semi-supervised learning and automatic labeling strategies can be an asset for training deep neural networks. However, the quality of the automatically generated…

Machine Learning · Computer Science 2022-03-04 Wenhui Cui , Haleh Akrami , Anand A. Joshi , Richard M. Leahy

Learning with a primary objective, such as softmax cross entropy for classification and sequence generation, has been the norm for training deep neural networks for years. Although being a widely-adopted approach, using cross entropy as the…

Machine Learning · Computer Science 2019-03-25 Hao-Yun Chen , Pei-Hsin Wang , Chun-Hao Liu , Shih-Chieh Chang , Jia-Yu Pan , Yu-Ting Chen , Wei Wei , Da-Cheng Juan

Supervised-contrastive loss (SCL) is an alternative to cross-entropy (CE) for classification tasks that makes use of similarities in the embedding space to allow for richer representations. In this work, we propose methods to engineer the…

Machine Learning · Computer Science 2023-10-03 Jaidev Gill , Vala Vakilian , Christos Thrampoulidis

Class-incremental learning of deep networks sequentially increases the number of classes to be classified. During training, the network has only access to data of one task at a time, where each task contains several classes. In this…

Computer Vision and Pattern Recognition · Computer Science 2020-04-02 Lu Yu , Bartłomiej Twardowski , Xialei Liu , Luis Herranz , Kai Wang , Yongmei Cheng , Shangling Jui , Joost van de Weijer

We explore loss functions for fact verification in the FEVER shared task. While the cross-entropy loss is a standard objective for training verdict predictors, it fails to capture the heterogeneity among the FEVER verdict classes. In this…

Computation and Language · Computer Science 2024-03-14 Yuta Mukobara , Yutaro Shigeto , Masashi Shimbo

With the recent promising results of contrastive learning in the self-supervised learning paradigm, supervised contrastive learning has successfully extended these contrastive approaches to supervised contexts, outperforming cross-entropy…

Computer Vision and Pattern Recognition · Computer Science 2023-05-23 Jaewon Kim , Hyukjong Lee , Jooyoung Chang , Sang Min Park

Empirical risk minimization (ERM) with a computationally feasible surrogate loss is a widely accepted approach for classification. Notably, the convexity and calibration (CC) properties of a loss function ensure consistency of ERM in…

Machine Learning · Statistics 2024-09-05 Ben Dai

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

In deep learning, classification tasks are formalized as optimization problems often solved via the minimization of the cross-entropy. However, recent advancements in the design of objective functions allow the usage of the $f$-divergence…

Machine Learning · Computer Science 2024-05-17 Nicola Novello , Andrea M. Tonello

We consider adversarially robust classification in a multiclass setting under arbitrary loss functions and derive dual and barycentric reformulations of the corresponding learner-agnostic robust risk minimization problem. We provide…

Machine Learning · Computer Science 2025-10-03 Camilo Andrés García Trillos , Nicolás García Trillos

Standard cross-entropy is the default classification loss across virtually all of machine learning, yet it treats all misclassifications equally, ignoring the semantic distances that a class hierarchy encodes. We propose Hierarchy-Aware…

Machine Learning · Computer Science 2026-05-08 April Chan , Davide D'Ascenzo , Sebastiano Cultrera di Montesano

Semi-supervised learning is attracting blooming attention, due to its success in combining unlabeled data. To mitigate potentially incorrect pseudo labels, recent frameworks mostly set a fixed confidence threshold to discard uncertain…

Computer Vision and Pattern Recognition · Computer Science 2023-08-15 Lihe Yang , Zhen Zhao , Lei Qi , Yu Qiao , Yinghuan Shi , Hengshuang Zhao

A large amount of research on Convolutional Neural Networks has focused on flat Classification in the multi-class domain. In the real world, many problems are naturally expressed as problems of hierarchical classification, in which the…

Computer Vision and Pattern Recognition · Computer Science 2020-05-19 Riccardo La Grassa , Ignazio Gallo , Nicola Landro

Neural image classification models typically consist of two components. The first is an image encoder, which is responsible for encoding a given raw image into a representative vector. The second is the classification component, which is…

Machine Learning · Computer Science 2020-12-01 Gabi Shalev , Gal-Lev Shalev , Joseph Keshet

For classification, neural networks typically learn by minimizing cross-entropy, but are evaluated and compared using accuracy. This disparity suggests neural loss function search (NLFS), the search for a drop-in replacement loss function…

Computer Vision and Pattern Recognition · Computer Science 2024-03-15 Brandon Morgan , Dean Hougen

Given data with label noise (i.e., incorrect data), deep neural networks would gradually memorize the label noise and impair model performance. To relieve this issue, curriculum learning is proposed to improve model performance and…

Machine Learning · Computer Science 2022-08-23 Tingting Wu , Xiao Ding , Hao Zhang , Jinglong Gao , Li Du , Bing Qin , Ting Liu

We develop new approaches in multi-class settings for constructing proper scoring rules and hinge-like losses and establishing corresponding regret bounds with respect to the zero-one or cost-weighted classification loss. Our construction…

Statistics Theory · Mathematics 2021-05-18 Zhiqiang Tan , Xinwei Zhang