English
Related papers

Related papers: Online normalizer calculation for softmax

200 papers

We present the soft exponential activation function for artificial neural networks that continuously interpolates between logarithmic, linear, and exponential functions. This activation function is simple, differentiable, and parameterized…

Neural and Evolutionary Computing · Computer Science 2016-02-04 Luke B. Godfrey , Michael S. Gashler

Mutual information is widely applied to learn latent representations of observations, whilst its implication in classification neural networks remain to be better explained. We show that optimising the parameters of classification neural…

Machine Learning · Computer Science 2020-09-18 Zhenyue Qin , Dongwoo Kim , Tom Gedeon

Large language models rely on attention mechanisms with a softmax activation. Yet the dominance of softmax over alternatives (e.g., component-wise or linear) remains poorly understood, and many theoretical works have focused on the…

Machine Learning · Computer Science 2026-02-27 O. Duranthon , P. Marion , C. Boyer , B. Loureiro , L. Zdeborová

In a multi-class classification problem, it is standard to model the output of a neural network as a categorical distribution conditioned on the inputs. The output must therefore be positive and sum to one, which is traditionally enforced…

Neural and Evolutionary Computing · Computer Science 2016-03-01 Alexandre de Brébisson , Pascal Vincent

We propose an accelerated meta-algorithm, which allows to obtain accelerated methods for convex unconstrained minimization in different settings. As an application of the general scheme we propose nearly optimal methods for minimizing…

We consider sequential maximization of performance metrics that are general functions of a confusion matrix of a classifier (such as precision, F-measure, or G-mean). Such metrics are, in general, non-decomposable over individual instances,…

Machine Learning · Computer Science 2024-06-24 Wojciech Kotłowski , Marek Wydmuch , Erik Schultheis , Rohit Babbar , Krzysztof Dembczyński

The computational cost of training with softmax cross entropy loss grows linearly with the number of classes. For the settings where a large number of classes are involved, a common method to speed up training is to sample a subset of…

Machine Learning · Computer Science 2020-01-01 Ankit Singh Rawat , Jiecao Chen , Felix Yu , Ananda Theertha Suresh , Sanjiv Kumar

We provide a systematic recipe for translating ReLU approximation results to softmax attention mechanism. This recipe covers many common approximation targets. Importantly, it yields target-specific, economic resource bounds beyond…

Machine Learning · Computer Science 2026-04-29 Jerry Yao-Chieh Hu , Mingcheng Lu , Yi-Chen Lee , Han Liu

We propose DropMax, a stochastic version of softmax classifier which at each iteration drops non-target classes according to dropout probabilities adaptively decided for each instance. Specifically, we overlay binary masking variables over…

Machine Learning · Computer Science 2018-11-05 Hae Beom Lee , Juho Lee , Saehoon Kim , Eunho Yang , Sung Ju Hwang

We propose \emph{MaxUp}, an embarrassingly simple, highly effective technique for improving the generalization performance of machine learning models, especially deep neural networks. The idea is to generate a set of augmented data with…

Machine Learning · Computer Science 2020-02-24 Chengyue Gong , Tongzheng Ren , Mao Ye , Qiang Liu

This paper presents a neural network optimizer with soft-argmax operator to achieve an ecological gearshift strategy in real-time. The strategy is reformulated as the mixed-integer model predictive control (MIMPC) problem to minimize energy…

Systems and Control · Electrical Eng. & Systems 2024-02-29 Xi Luo , Shiying Dong , Jinlong Hong , Bingzhao Gao , Hong Chen

Noisy labels pose a common challenge for training accurate deep neural networks. To mitigate label noise, prior studies have proposed various robust loss functions to achieve noise tolerance in the presence of label noise, particularly…

Machine Learning · Computer Science 2025-08-05 Jialiang Wang , Xiong Zhou , Deming Zhai , Junjun Jiang , Xiangyang Ji , Xianming Liu

In this study, SoftReMish, a new activation function designed to improve the performance of convolutional neural networks (CNNs) in image classification tasks, is proposed. Using the MNIST dataset, a standard CNN architecture consisting of…

Computer Vision and Pattern Recognition · Computer Science 2025-07-09 Mustafa Bayram Gücen

This work proposes an accelerated first-order algorithm we call the Robust Momentum Method for optimizing smooth strongly convex functions. The algorithm has a single scalar parameter that can be tuned to trade off robustness to gradient…

Optimization and Control · Mathematics 2018-02-27 Saman Cyrus , Bin Hu , Bryan Van Scoy , Laurent Lessard

Training a classifier over a large number of classes, known as 'extreme classification', has become a topic of major interest with applications in technology, science, and e-commerce. Traditional softmax regression induces a gradient cost…

Machine Learning · Statistics 2020-02-18 Robert Bamler , Stephan Mandt

Attention architectures are widely used; they recently gained renewed popularity with Transformers yielding a streak of state of the art results. Yet, the geometrical implications of softmax-attention remain largely unexplored. In this work…

Machine Learning · Computer Science 2020-05-20 Oliver Richter , Roger Wattenhofer

Over-the-Air Computation is a beyond-5G communication strategy that has recently been shown to be useful for the decentralized training of machine learning models due to its efficiency. In this paper, we propose an Over-the-Air federated…

Machine Learning · Computer Science 2024-03-08 Halil Yigit Oksuz , Fabio Molinari , Henning Sprekeler , Joerg Raisch

Uncertainty approximation in text classification is an important area with applications in domain adaptation and interpretability. One of the most widely used uncertainty approximation methods is Monte Carlo (MC) Dropout, which is…

Machine Learning · Computer Science 2023-07-20 Andreas Nugaard Holm , Dustin Wright , Isabelle Augenstein

Online Normalization is a new technique for normalizing the hidden activations of a neural network. Like Batch Normalization, it normalizes the sample dimension. While Online Normalization does not use batches, it is as accurate as Batch…

Simplex-structured matrix factorization (SSMF) is a common task encountered in signal processing and machine learning. Minimum-volume constrained unmixing (MVCU) algorithms are among the most widely used methods to perform this task. While…

‹ Prev 1 3 4 5 6 7 10 Next ›