English
Related papers

Related papers: Adaptive Sparse Softmax: An Effective and Efficien…

200 papers

Current sequence-to-sequence models are trained to minimize cross-entropy and use softmax to compute the locally normalized probabilities over target sequences. While this setup has led to strong results in a variety of tasks, one…

Computation and Language · Computer Science 2021-03-19 Ben Peters , André F. T. Martins

Soft targets combined with the cross-entropy loss have shown to improve generalization performance of deep neural networks on supervised classification tasks. The standard cross-entropy loss however assumes data to be categorically…

Machine Learning · Computer Science 2024-07-16 Johannes Hugger , Virginie Uhlmann

SoftMax is a ubiquitous ingredient of modern machine learning algorithms. It maps an input vector onto a probability simplex and reweights the input by concentrating the probability mass at large entries. Yet, as a smooth approximation to…

Machine Learning · Computer Science 2025-01-09 Yuxuan Zhou , Mario Fritz , Margret Keuper

The softmax function is crucial in Transformer attention, which normalizes each row of the attention scores with summation to one, achieving superior performances over other alternative functions. However, the softmax function can face a…

Computation and Language · Computer Science 2025-02-26 Chuanyang Zheng , Yihang Gao , Guoxuan Chen , Han Shi , Jing Xiong , Xiaozhe Ren , Chao Huang , Xin Jiang , Zhenguo Li , Yu Li

The learning objective plays a fundamental role to build a recommender system. Most methods routinely adopt either pointwise or pairwise loss to train the model parameters, while rarely pay attention to softmax loss due to its computational…

Information Retrieval · Computer Science 2023-12-20 Jiancan Wu , Xiang Wang , Xingyu Gao , Jiawei Chen , Hongcheng Fu , Tianyu Qiu

Distance metric learning (DML) approaches learn a transformation to a representation space where distance is in correspondence with a predefined notion of similarity. While such models offer a number of compelling benefits, it has been…

Machine Learning · Statistics 2016-03-03 Oren Rippel , Manohar Paluri , Piotr Dollar , Lubomir Bourdev

Conformal prediction is a distribution-free framework for uncertainty quantification that replaces point predictions with sets, offering marginal coverage guarantees (i.e., ensuring that the prediction sets contain the true label with a…

Machine Learning · Computer Science 2025-02-25 Margarida M. Campos , João Calém , Sophia Sklaviadis , Mário A. T. Figueiredo , André F. T. Martins

We propose an adaptive training scheme for unsupervised medical image registration. Existing methods rely on image reconstruction as the primary supervision signal. However, nuisance variables (e.g. noise and covisibility), violation of the…

Image and Video Processing · Electrical Eng. & Systems 2024-07-19 Xiaoran Zhang , John C. Stendahl , Lawrence Staib , Albert J. Sinusas , Alex Wong , James S. Duncan

The softmax loss and its variants are widely used as objectives for embedding learning, especially in applications like face recognition. However, the intra- and inter-class objectives in the softmax loss are entangled, therefore a…

Computer Vision and Pattern Recognition · Computer Science 2020-02-13 Lanqing He , Zhongdao Wang , Yali Li , Shengjin Wang

Stochastic gradient decent~(SGD) and its variants, including some accelerated variants, have become popular for training in machine learning. However, in all existing SGD and its variants, the sample size in each iteration~(epoch) of…

Machine Learning · Statistics 2019-09-18 Shen-Yi Zhao , Hao Gao , Wu-Jun Li

Softmax is widely used in neural networks for multiclass classification, gate structure and attention mechanisms. The statistical assumption that the input is normal distributed supports the gradient stability of Softmax. However, when used…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Shulun Wang , Bin Liu , Feng Liu

Softmax classifiers with a very large number of classes naturally occur in many applications such as natural language processing and information retrieval. The calculation of full softmax is costly from the computational and energy…

Machine Learning · Computer Science 2021-07-30 Shabnam Daghaghi , Tharun Medini , Nicholas Meisburger , Beidi Chen , Mengnan Zhao , Anshumali Shrivastava

In real-world applications, machine learning models face online label shift, where label distributions change over time. Effective adaptation requires careful learning rate selection: too low slows adaptation and too high causes…

Machine Learning · Computer Science 2025-08-20 Heewon Park , Mugon Joe , Miru Kim , Minhae Kwon

Motivated by extreme multi-label classification applications, we consider training deep learning models over sparse data in multi-GPU servers. The variance in the number of non-zero features across training batches and the intrinsic GPU…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-10-15 Yujing Ma , Florin Rusu , Kesheng Wu , Alexander Sim

Massive datasets often contain redundancy that inflates computational costs without improving generalization. Existing data reduction methods are typically task-agnostic, discarding informative boundary samples and yielding suboptimal…

Machine Learning · Computer Science 2026-04-07 Jiacheng Lyu , Bihua Bao , Shiyun Yan

In replay-based methods for continual learning, replaying input samples in episodic memory has shown its effectiveness in alleviating catastrophic forgetting. However, the potential key factor of cross-entropy loss with softmax in causing…

Machine Learning · Computer Science 2024-01-25 Hoyong Kim , Minchan Kwon , Kangil Kim

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

Replicated Softmax model, a well-known undirected topic model, is powerful in extracting semantic representations of documents. Traditional learning strategies such as Contrastive Divergence are very inefficient. This paper provides a novel…

Machine Learning · Computer Science 2015-06-25 Jiatao Gu , Victor O. K. Li

Traditionally artificial neural networks (ANNs) are trained by minimizing the cross-entropy between a provided groundtruth delta distribution (encoded as one-hot vector) and the ANN's predictive softmax distribution. It seems, however,…

Computer Vision and Pattern Recognition · Computer Science 2018-12-31 Pooran Singh Negi , David chan , Mohammad Mahoor

Softmax is a standard final layer used in Neural Nets (NNs) to summarize information encoded in the trained NN and return a prediction. However, Softmax leverages only a subset of the class-specific structure encoded in the trained model…

Machine Learning · Computer Science 2019-12-09 Charles B. Delahunt , Courosh Mehanian , J. Nathan Kutz