English
Related papers

Related papers: From Softmax to Sparsemax: A Sparse Model of Atten…

200 papers

There is a growing need for models that are interpretable and have reduced energy and computational cost (e.g., in health care analytics and federated learning). Examples of algorithms to train such models include logistic regression and…

Machine Learning · Computer Science 2023-02-21 Tyler Sypherd , Nathan Stromberg , Richard Nock , Visar Berisha , Lalitha Sankar

Attention models are typically learned by optimizing one of three standard loss functions that are variously called -- soft attention, hard attention, and latent variable marginal likelihood (LVML) attention. All three paradigms are…

Machine Learning · Computer Science 2023-10-16 Rahul Vashisht , Harish G. Ramaswamy

The softmax layer in neural machine translation is designed to model the distribution over mutually exclusive tokens. Machine translation, however, is intrinsically uncertain: the same source sentence can have multiple semantically…

Computation and Language · Computer Science 2022-05-03 Felix Stahlberg , Shankar Kumar

The softmax function is a cornerstone of multi-class classification, integral to a wide range of machine learning applications, from large-scale retrieval and ranking models to advanced large language models. However, its computational cost…

Machine Learning · Computer Science 2025-01-16 Jin Chen , Jin Zhang , Xu huang , Yi Yang , Defu Lian , Enhong Chen

The softmax representation of probabilities for categorical variables plays a prominent role in modern machine learning with numerous applications in areas such as large scale classification, neural language modeling and recommendation…

Machine Learning · Statistics 2016-11-01 Michalis K. Titsias

The problem of devising learning strategies for discrete losses (e.g., multilabeling, ranking) is currently addressed with methods and theoretical analyses ad-hoc for each loss. In this paper we study a least-squares framework to…

Machine Learning · Computer Science 2018-10-17 Alex Nowak-Vila , Francis Bach , Alessandro Rudi

Softmax is an output activation function for modeling categorical probability distributions in many applications of deep learning. However, a recent study revealed that softmax can be a bottleneck of representational capacity of neural…

Machine Learning · Statistics 2018-05-29 Sekitoshi Kanai , Yasuhiro Fujiwara , Yuki Yamanaka , Shuichi Adachi

Transformers' quadratic complexity with respect to the input sequence length has motivated a body of work on efficient sparse approximations to softmax. An alternative path, used by entmax transformers, consists of having built-in exact…

Computation and Language · Computer Science 2022-04-22 Marcos Treviso , António Góis , Patrick Fernandes , Erick Fonseca , André F. T. Martins

Attention mechanisms have been extensively employed in various applications, including time series modeling, owing to their capacity to capture intricate dependencies; however, their utility is often constrained by quadratic computational…

Machine Learning · Computer Science 2025-11-06 Mingtao Zhang , Guoli Yang , Zhanxing Zhu , Mengzhu Wang , Xiaoying Bai

While linear attention reduces the quadratic complexity of standard Transformers to linear time, it often lags behind in expressivity due to the removal of softmax normalization. This omission eliminates \emph{global competition}, a…

Machine Learning · Computer Science 2026-02-03 Mingwei Xu , Xuan Lin , Xinnan Guo , Wanqing Xu , Wanyun Cui

Due to its linear complexity, naive Bayes classification remains an attractive supervised learning method, especially in very large-scale settings. We propose a sparse version of naive Bayes, which can be used for feature selection. This…

Machine Learning · Computer Science 2025-03-13 Armin Askari , Alexandre d'Aspremont , Laurent El Ghaoui

Various forms of sparse attention have been explored to mitigate the quadratic computational and memory cost of the attention mechanism in transformers. We study sparse transformers not through a lens of efficiency but rather in terms of…

Machine Learning · Computer Science 2025-06-19 Parikshit Ram , Kenneth L. Clarkson , Tim Klinger , Shashanka Ubaru , Alexander G. Gray

A new line of research for feature selection based on neural networks has recently emerged. Despite its superiority to classical methods, it requires many training iterations to converge and detect informative features. The computational…

Machine Learning · Computer Science 2022-11-29 Ghada Sokar , Zahra Atashgahi , Mykola Pechenizkiy , Decebal Constantin Mocanu

The softmax content-based attention mechanism has proven to be very beneficial in many applications of recurrent neural networks. Nevertheless it suffers from two major computational limitations. First, its computations for an attention…

Machine Learning · Computer Science 2016-09-20 Alexandre de Brébisson , Pascal Vincent

This paper addresses the scalar regression problem through a novel solution to exactly optimize the Huber loss in a general semi-supervised setting, which combines multi-view learning and manifold regularization. We propose a principled…

Machine Learning · Computer Science 2016-06-28 Jacopo Cavazza , Vittorio Murino

This paper focuses on detection tasks in information extraction, where positive instances are sparsely distributed and models are usually evaluated using F-measure on positive classes. These characteristics often result in deficient…

Computation and Language · Computer Science 2018-05-29 Hongyu Lin , Yaojie Lu , Xianpei Han , Le Sun

In recent years, the attention mechanism contributes significantly to hypergraph based neural networks. However, these methods update the attention weights with the network propagating. That is to say, this type of attention mechanism is…

Computer Vision and Pattern Recognition · Computer Science 2020-10-26 Shuai Shao , Rui Xu , Yan-Jiang Wang , Weifeng Liu , Bao-Di Liu

Large language models (LLMs) have made transformed changes for human society. One of the key computation in LLMs is the softmax unit. This operation is important in LLMs because it allows the model to generate a distribution over possible…

Machine Learning · Computer Science 2023-04-27 Yichuan Deng , Zhihang Li , Zhao Song

Softmax working with cross-entropy is widely used in classification, which evaluates the similarity between two discrete distribution columns (predictions and true labels). Inspired by chi-square test, we designed a new loss function called…

Machine Learning · Computer Science 2021-09-01 Zeyu Wang , Meiqing Wang

Leveraging the wealth of unlabeled data produced in recent years provides great potential for improving supervised models. When the cost of acquiring labels is high, probabilistic active learning methods can be used to greedily select the…

Machine Learning · Statistics 2021-02-09 Robert Pinsler , Jonathan Gordon , Eric Nalisnick , José Miguel Hernández-Lobato