English
Related papers

Related papers: Exploring Alternatives to Softmax Function

200 papers

Metalearning of deep neural network (DNN) architectures and hyperparameters has become an increasingly important area of research. Loss functions are a type of metaknowledge that is crucial to effective training of DNNs, however, their…

Machine Learning · Computer Science 2020-10-05 Santiago Gonzalez , Risto Miikkulainen

State-of-the-art face recognition methods typically take the multi-classification pipeline and adopt the softmax-based loss for optimization. Although these methods have achieved great success, the softmax-based loss has its limitation from…

Computer Vision and Pattern Recognition · Computer Science 2023-02-13 Lizhe Liu , Mingqiang Chen , Xiaohao Chen , Siyu Zhu , Ping Tan

Adaptive loss function formulation is an active area of research and has gained a great deal of popularity in recent years, following the success of deep learning. However, existing frameworks of adaptive loss functions often suffer from…

Machine Learning · Computer Science 2020-01-01 A. Ali Heydari , Craig A. Thompson , Asif Mehmood

We present a formulation of deep learning that aims at producing a large margin classifier. The notion of margin, minimum distance to a decision boundary, has served as the foundation of several theoretically profound and empirically…

Machine Learning · Statistics 2018-12-05 Gamaleldin F. Elsayed , Dilip Krishnan , Hossein Mobahi , Kevin Regan , Samy Bengio

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

Multi-class text classification is one of the key problems in machine learning and natural language processing. Emerging neural networks deal with the problem using a multi-output softmax layer and achieve substantial progress, but they do…

Computation and Language · Computer Science 2020-03-26 Haiyang Xu , Junwen Chen , Kun Han , Xiangang Li

The maximum element of the vector output by the Softmax function approaches zero as the input vector size increases. Transformer-based language models rely on Softmax to compute attention scores, causing the attention distribution to…

Computation and Language · Computer Science 2025-02-03 Ken M. Nakanishi

Transformers have transformed the field of natural language processing. This performance is largely attributed to the use of stacked self-attention layers, each of which consists of matrix multiplies as well as softmax operations. As a…

Hardware Architecture · Computer Science 2021-03-18 Jacob R. Stevens , Rangharajan Venkatesan , Steve Dai , Brucek Khailany , Anand Raghunathan

Aiming to enhance the utilization of metric space by the parametric softmax classifier, recent studies suggest replacing it with a non-parametric alternative. Although a non-parametric classifier may provide better metric space utilization,…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Mohammad Saeed Ebrahimi Saadabadi , Ali Dabouei , Sahar Rahimi Malakshan , Nasser M. Nasrabad

We replace the output layer of deep neural nets, typically the softmax function, by a novel interpolating function. And we propose end-to-end training and testing algorithms for this new architecture. Compared to classical neural nets with…

Machine Learning · Computer Science 2018-06-19 Bao Wang , Xiyang Luo , Zhen Li , Wei Zhu , Zuoqiang Shi , Stanley J. Osher

Softmax is popular normalization method used in machine learning. Deep learning solutions like Transformer or BERT use the softmax function intensively, so it is worthwhile to optimize its performance. This article presents our methodology…

Mathematical Software · Computer Science 2019-05-28 Jacek Czaja , Michal Gallus , Tomasz Patejko , Jian Tang

Recently, Transformer networks have demonstrated outstanding performance in the field of image restoration due to the global receptive field and adaptability to input. However, the quadratic computational complexity of Softmax-attention…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Zhi Jin , Yuwei Qiu , Kaihao Zhang , Hongdong Li , Wenhan Luo

Neural machine translation (NMT) models are typically trained using a softmax cross-entropy loss where the softmax distribution is compared against smoothed gold labels. In low-resource scenarios, NMT models tend to over-fit because the…

Computation and Language · Computer Science 2020-09-22 Raj Dabre , Atsushi Fujita

Softmax with the cross entropy loss is the standard configuration for current neural classification models. The gold score for a target class is supposed to be 1, but it is never reachable under the softmax schema. Such a problem makes the…

Machine Learning · Computer Science 2025-08-06 Qi Lv , Lei Geng , Ziqiang Cao , Min Cao , Sujian Li , Wenjie Li , Guohong Fu

Building upon recent advances in entropy-regularized optimal transport, and upon Fenchel duality between measures and continuous functions , we propose a generalization of the logistic loss that incorporates a metric or cost between…

Machine Learning · Statistics 2019-05-16 Arthur Mensch , Mathieu Blondel , Gabriel Peyré

Researches using margin based comparison loss demonstrate the effectiveness of penalizing the distance between face feature and their corresponding class centers. Despite their popularity and excellent performance, they do not explicitly…

Computer Vision and Pattern Recognition · Computer Science 2020-06-12 Ying Huang , Shangfeng Qiu , Wenwei Zhang , Xianghui Luo , Jinzhuo Wang

Class imbalance remains a major challenge in machine learning, especially in multi-class problems with long-tailed distributions. Existing methods, such as data resampling, cost-sensitive techniques, and logistic loss modifications, though…

Machine Learning · Computer Science 2025-12-30 Corinna Cortes , Anqi Mao , Mehryar Mohri , Yutao Zhong

Convolutional Neural Networks (CNNs) trained with the Softmax loss are widely used classification models for several vision tasks. Typically, a learnable transformation (i.e. the classifier) is placed at the end of such models returning…

Computer Vision and Pattern Recognition · Computer Science 2023-01-18 Federico Pernici , Matteo Bruni , Claudio Baecchi , Alberto Del Bimbo

The binomial deviance and the SVM hinge loss functions are two of the most widely used loss functions in machine learning. While there are many similarities between them, they also have their own strengths when dealing with different types…

Machine Learning · Statistics 2022-05-25 Man Huang , Luis Carvalho

Deep classifiers have achieved great success in visual recognition. However, real-world data is long-tailed by nature, leading to the mismatch between training and testing distributions. In this report, we introduce Balanced Activation…

Machine Learning · Computer Science 2020-08-26 Jiawei Ren , Cunjun Yu , Zhongang Cai , Haiyu Zhao