English
Related papers

Related papers: Be Careful What You Backpropagate: A Case For Line…

200 papers

Binary neural networks leverage $\mathrm{Sign}$ function to binarize weights and activations, which require gradient estimators to overcome its non-differentiability and will inevitably bring gradient errors during backpropagation. Although…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Yefei He , Luoming Zhang , Weijia Wu , Hong Zhou

Normalization methods improve both optimization and generalization of ConvNets. To further boost performance, the recently-proposed switchable normalization (SN) provides a new perspective for deep learning: it learns to select different…

Computer Vision and Pattern Recognition · Computer Science 2019-03-12 Wenqi Shao , Tianjian Meng , Jingyu Li , Ruimao Zhang , Yudian Li , Xiaogang Wang , Ping Luo

Fine-grained image recognition is central to many multimedia tasks such as search, retrieval and captioning. Unfortunately, these tasks are still challenging since the appearance of samples of the same class can be more different than those…

Computer Vision and Pattern Recognition · Computer Science 2019-07-31 Pau Rodríguez López , Diego Velazquez Dorta , Guillem Cucurull Preixens , Josep M. Gonfaus , F. Xavier Roca Marva , Jordi Gonzàlez Sabaté

Policy gradient (PG) estimators are ineffective in dealing with softmax policies that are sub-optimally saturated, which refers to the situation when the policy concentrates its probability mass on sub-optimal actions. Sub-optimal policy…

Machine Learning · Computer Science 2022-02-25 Shivam Garg , Samuele Tosatto , Yangchen Pan , Martha White , A. Rupam Mahmood

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 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

Recently, fully-connected and convolutional neural networks have been trained to achieve state-of-the-art performance on a wide variety of tasks such as speech recognition, image classification, natural language processing, and…

Machine Learning · Computer Science 2015-02-24 Yichuan Tang

Hard-label classification is usually trained with smooth surrogate losses, most prominently softmax cross-entropy. We isolate an asymptotic mechanism by which this mismatch between smooth surrogate and discrete labels produces power-law…

Machine Learning · Computer Science 2026-05-22 Marcel Kühn , Yoon Thelge , Bernd Rosenow

Modern neural networks are over-parameterized and thus rely on strong regularization such as data augmentation and weight decay to reduce overfitting and improve generalization. The dominant form of data augmentation applies invariant…

Computer Vision and Pattern Recognition · Computer Science 2024-01-25 Yang Liu , Shen Yan , Laura Leal-Taixé , James Hays , Deva Ramanan

The softmax activation function plays a crucial role in the success of large language models (LLMs), particularly in the self-attention mechanism of the widely adopted Transformer architecture. However, the underlying learning dynamics that…

Machine Learning · Computer Science 2026-01-27 Yang Cao , Yingyu Liang , Zhenmei Shi , Zhao Song

Despite achieving state-of-the-art results in nearly all Natural Language Processing applications, fine-tuning Transformer-based language models still requires a significant amount of labeled data to work. A well known technique to reduce…

Machine Learning · Computer Science 2025-03-13 Julius Gonsior , Christian Falkenberg , Silvio Magino , Anja Reusch , Maik Thiele , Wolfgang Lehner

Despite the undeniable progress in visual recognition tasks fueled by deep neural networks, there exists recent evidence showing that these models are poorly calibrated, resulting in over-confident predictions. The standard practices of…

Computer Vision and Pattern Recognition · Computer Science 2024-02-01 Balamurali Murugesan , Bingyuan Liu , Adrian Galdran , Ismail Ben Ayed , Jose Dolz

Policy-gradient approaches to reinforcement learning have two common and undesirable overhead procedures, namely warm-start training and sample variance reduction. In this paper, we describe a reinforcement learning method based on a…

Machine Learning · Computer Science 2017-10-17 Nan Ding , Radu Soricut

The Softmax activation layer is a very popular Deep Neural Network (DNN) component when dealing with multi-class prediction problems. However, in DNN accelerator implementations it creates additional complexities due to the need for…

Hardware Architecture · Computer Science 2022-01-13 Raghuram S

This paper presents a computationally efficient variant of gradient boosting for multi-class classification and multi-output regression tasks. Standard gradient boosting uses a 1-vs-all strategy for classifications tasks with more than two…

Machine Learning · Computer Science 2024-07-25 Seyedsaman Emami , Gonzalo Martínez-Muñoz

We illustrate the detrimental effect, such as overconfident decisions, that exponential behavior can have in methods like classical LDA and logistic regression. We then show how polynomiality can remedy the situation. This, among others,…

Machine Learning · Computer Science 2022-03-25 Ziqi Wang , Marco Loog

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

Non-local (NL) block is a popular module that demonstrates the capability to model global contexts. However, NL block generally has heavy computation and memory costs, so it is impractical to apply the block to high-resolution feature maps.…

Computer Vision and Pattern Recognition · Computer Science 2022-07-28 Yooshin Cho , Youngsoo Kim , Hanbyel Cho , Jaesung Ahn , Hyeong Gwon Hong , Junmo Kim

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

Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates…

Machine Learning · Computer Science 2015-03-03 Sergey Ioffe , Christian Szegedy