English
Related papers

Related papers: Diagonalizing the Softmax: Hadamard Initialization…

200 papers

Optimization analyses for cross-entropy training rely on local Taylor models of the loss to predict whether a proposed step will decrease the objective. These surrogates are reliable only inside the Taylor convergence radius of the true…

Machine Learning · Computer Science 2026-03-17 Piyush Sao

Distance metric learning (DML) is to learn the embeddings where examples from the same class are closer than examples from different classes. It can be cast as an optimization problem with triplet constraints. Due to the vast number of…

Computer Vision and Pattern Recognition · Computer Science 2020-04-16 Qi Qian , Lei Shang , Baigui Sun , Juhua Hu , Hao Li , Rong Jin

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

The key factor in implementing machine learning algorithms in decision-making situations is not only the accuracy of the model but also its confidence level. The confidence level of a model in a classification problem is often given by the…

Machine Learning · Statistics 2024-05-02 Masanari Kimura , Hiroki Naganuma

In this paper, we present a cross-entropy optimization method for hyperparameter optimization in stochastic gradient-based approaches to train deep neural networks. The value of a hyperparameter of a learning algorithm often has great…

Machine Learning · Computer Science 2024-09-17 Kevin Li , Fulu Li

Although transformer-based models have shown exceptional empirical performance, the fundamental principles governing their training dynamics are inadequately characterized beyond configuration-specific studies. Inspired by empirical…

Machine Learning · Computer Science 2025-10-09 Zheng-An Chen , Tao Luo

Equivariant neural networks are designed to respect symmetries through their architecture, boosting generalization and sample efficiency when those symmetries are present in the data distribution. Real-world data, however, often departs…

Machine Learning · Computer Science 2025-12-12 Andrei Manolache , Luiz F. O. Chamon , Mathias Niepert

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

Deep learning is increasingly viewed as a dynamical process in parameter space, yet many existing theories still treat training as a closed optimization system. This view is limited for real-world AI, where models operate under uncertainty,…

Machine Learning · Computer Science 2026-05-25 Kim Phuc Tran

We show that learning can be improved by using loss functions that evolve cyclically during training to emphasize one class at a time. In underparameterized networks, such dynamical loss functions can lead to successful training for…

Machine Learning · Computer Science 2021-06-24 Miguel Ruiz-Garcia , Ge Zhang , Samuel S. Schoenholz , Andrea J. Liu

With the development of convolutional neural networks (CNNs) in recent years, the network structure has become more and more complex and varied, and has achieved very good results in pattern recognition, image classification, object…

Computer Vision and Pattern Recognition · Computer Science 2019-04-29 Qiuyu Zhu , Pengju Zhang , Xin Ye

In this paper, we focus on the separability of classes with the cross-entropy loss function for classification problems by theoretically analyzing the intra-class distance and inter-class distance (i.e. the distance between any two points…

Machine Learning · Computer Science 2019-09-17 Rudrajit Das , Subhasis Chaudhuri

In this paper, we prove a conjecture published in 1989 and also partially address an open problem announced at the Conference on Learning Theory (COLT) 2015. With no unrealistic assumption, we first prove the following statements for the…

Machine Learning · Statistics 2016-12-30 Kenji Kawaguchi

Identifying the heterogeneous conductivity field and reconstructing the contaminant release history are key aspects of subsurface remediation. Achieving these two goals with limited and noisy hydraulic head and concentration measurements is…

Machine Learning · Computer Science 2022-09-29 Zitong Zhou , Nicholas Zabaras , Daniel M. Tartakovsky

Deep neural networks (DNNs) have achieved state-of-the-art results in various pattern recognition tasks. However, they perform poorly on out-of-distribution adversarial examples i.e. inputs that are specifically crafted by an adversary to…

Cryptography and Security · Computer Science 2019-05-09 Chirag Agarwal , Anh Nguyen , Dan Schonfeld

We study the optimization landscape of deep linear neural networks with the square loss. It is known that, under weak assumptions, there are no spurious local minima and no local maxima. However, the existence and diversity of non-strict…

Statistics Theory · Mathematics 2024-09-26 El Mehdi Achour , François Malgouyres , Sébastien Gerchinovitz

Cross-entropy is a widely used loss function in applications. It coincides with the logistic loss applied to the outputs of a neural network, when the softmax is used. But, what guarantees can we rely on when using cross-entropy as a…

Machine Learning · Computer Science 2023-06-21 Anqi Mao , Mehryar Mohri , Yutao Zhong

Gradient descent and coordinate descent are well understood in terms of their asymptotic behavior, but less so in a transient regime often used for approximations in machine learning. We investigate how proper initialization can have a…

Machine Learning · Computer Science 2017-06-14 Hadi Daneshmand , Hamed Hassani , Thomas Hofmann

Cross-entropy loss with softmax output is a standard choice to train neural network classifiers. We give a new view of neural network classifiers with softmax and cross-entropy as mutual information evaluators. We show that when the dataset…

Machine Learning · Computer Science 2021-08-17 Zhenyue Qin , Dongwoo Kim , Tom Gedeon

State-of-the-art pre-trained image models predominantly adopt a two-stage approach: initial unsupervised pre-training on large-scale datasets followed by task-specific fine-tuning using Cross-Entropy loss~(CE). However, it has been…

Computer Vision and Pattern Recognition · Computer Science 2024-11-18 Zijun Long , George Killick , Lipeng Zhuang , Gerardo Aragon-Camarasa , Zaiqiao Meng , Richard Mccreadie