English
Related papers

Related papers: Dynamical loss functions shape landscape topograph…

200 papers

In this paper, we explore the application of mean field theory, a technique from statistical physics, to deep metric learning and address the high training complexity commonly associated with conventional metric learning loss functions. By…

Machine Learning · Computer Science 2023-06-28 Takuya Furusawa

We study the dynamics of optimization and the generalization properties of one-hidden layer neural networks with quadratic activation function in the over-parametrized regime where the layer width $m$ is larger than the input dimension $d$.…

Machine Learning · Computer Science 2021-03-22 Stefano Sarao Mannelli , Eric Vanden-Eijnden , Lenka Zdeborová

This paper explores the intricate behavior of deep neural networks (DNNs) through the lens of neuron activation dynamics. We propose a probabilistic framework that can analyze models' neuron activation patterns as a stochastic process,…

Artificial Intelligence · Computer Science 2024-12-25 Yizhou Zhang , Yang Sui

We propose a stepsize adaptation scheme for stochastic gradient descent. It operates directly with the loss function and rescales the gradient in order to make fixed predicted progress on the loss. We demonstrate its capabilities by…

Machine Learning · Computer Science 2018-12-03 Michal Rolinek , Georg Martius

A significant advance in accelerating neural network training has been the development of normalization methods, permitting the training of deep models both faster and with better accuracy. These advances come with practical challenges: for…

Machine Learning · Computer Science 2019-03-05 Jasmine Collins , Johannes Balle , Jonathon Shlens

Recent studies have highlighted that deep neural networks (DNNs) are vulnerable to adversarial examples. In this paper, we improve the robustness of DNNs by utilizing techniques of Distance Metric Learning. Specifically, we incorporate…

Machine Learning · Computer Science 2019-05-29 Pengcheng Li , Jinfeng Yi , Bowen Zhou , Lijun Zhang

Despite their practical success, a theoretical understanding of the loss landscape of neural networks has proven challenging due to the high-dimensional, non-convex, and highly nonlinear structure of such models. In this paper, we…

Machine Learning · Computer Science 2020-07-21 Abbas Kazemipour , Brett W. Larsen , Shaul Druckmann

Over the past decades, numerous loss functions have been been proposed for a variety of supervised learning tasks, including regression, classification, ranking, and more generally structured prediction. Understanding the core principles…

Machine Learning · Statistics 2020-03-03 Mathieu Blondel , André F. T. Martins , Vlad Niculae

Deep-learning architectures for classification problems involve the cross-entropy loss sometimes assisted with auxiliary loss functions like center loss, contrastive loss and triplet loss. These auxiliary loss functions facilitate better…

Computer Vision and Pattern Recognition · Computer Science 2020-04-22 Hongjun Choi , Anirudh Som , Pavan Turaga

The functionality of electronic circuits can be seriously impaired by the occurrence of dynamic hardware faults. Particularly, for digital ultra low-power systems, a reduced safety margin can increase the probability of dynamic failures.…

Machine Learning · Computer Science 2022-10-18 Daniel Gregorek , Nils Hülsmeier , Steffen Paul

The optimization foundations of deep linear networks have recently received significant attention. However, due to their inherent non-convexity and hierarchical structure, analyzing the loss functions of deep linear networks remains a…

Optimization and Control · Mathematics 2025-09-24 Po Chen , Rujun Jiang , Peng Wang

In this chapter, we utilize dynamical systems to analyze several aspects of machine learning algorithms. As an expository contribution we demonstrate how to re-formulate a wide variety of challenges from deep neural networks, (stochastic)…

Dynamical Systems · Mathematics 2025-07-08 Dennis Chemnitz , Maximilian Engel , Christian Kuehn , Sara-Viola Kuntz

Why do neural networks trained with large learning rates for a longer time often lead to better generalization? In this paper, we delve into this question by examining the relation between training and testing loss in neural networks.…

Machine Learning · Computer Science 2024-01-23 Yinuo Ren , Chao Ma , Lexing Ying

In recent years, deep perceptual loss has been widely and successfully used to train machine learning models for many computer vision tasks, including image synthesis, segmentation, and autoencoding. Deep perceptual loss is a type of loss…

Computer Vision and Pattern Recognition · Computer Science 2024-07-04 Gustav Grund Pihlgren , Konstantina Nikolaidou , Prakash Chandra Chhipa , Nosheen Abid , Rajkumar Saini , Fredrik Sandin , Marcus Liwicki

We propose a novel loss function that dynamically rescales the cross entropy based on prediction difficulty regarding a sample. Deep neural network architectures in image classification tasks struggle to disambiguate visually similar…

Computer Vision and Pattern Recognition · Computer Science 2019-09-26 Serim Ryou , Seong-Gyun Jeong , Pietro Perona

Cross-entropy loss has long been the standard choice for training deep neural networks, yet it suffers from interpretability limitations, unbounded weight growth, and inefficiencies that can contribute to costly training dynamics. The…

Machine Learning · Computer Science 2026-04-30 Maxwell Miller-Golub , Collin Coil , Kamil Faber , Marcin Pietron , Panpan Zheng , Pasquale Minervini , Roberto Corizzo

Recent studies showed that the generalization of neural networks is correlated with the sharpness of the loss landscape, and flat minima suggests a better generalization ability than sharp minima. In this paper, we propose a novel method…

Machine Learning · Computer Science 2024-05-24 Yuyan Zhou , Ye Li , Lei Feng , Sheng-Jun Huang

Training an artificial neural network involves an optimization process over the landscape defined by the cost (loss) as a function of the network parameters. We explore these landscapes using optimisation tools developed for potential…

Machine Learning · Statistics 2018-05-30 Dhagash Mehta , Xiaojun Zhao , Edgar A. Bernal , David J. Wales

Deep learning has been immensely successful at a variety of tasks, ranging from classification to AI. Learning corresponds to fitting training data, which is implemented by descending a very high-dimensional loss function. Understanding…

Disordered Systems and Neural Networks · Physics 2019-07-17 Mario Geiger , Stefano Spigler , Stéphane d'Ascoli , Levent Sagun , Marco Baity-Jesi , Giulio Biroli , Matthieu Wyart

Loss functions drive the optimization of machine learning algorithms. The choice of a loss function can have a significant impact on the training of a model, and how the model learns the data. Binary classification is one of the major…

Machine Learning · Computer Science 2022-11-02 Rayan Wali