English
Related papers

Related papers: Diagonalizing the Softmax: Hadamard Initialization…

200 papers

While machine learning (ML) architectures have evolved rapidly to account for complex data, loss functions like cross-entropy remain mostly structure-agnostic in many real-world applications. However, the `class-symmetric' nature of these…

Machine Learning · Computer Science 2026-05-28 Yasser Taha , Grégoire Montavon , Nils Körber

We introduce a constrained optimization framework for training transformers that behave like optimization descent algorithms. Specifically, we enforce layerwise descent constraints on the objective function and replace standard empirical…

Machine Learning · Computer Science 2026-01-27 Javier Porras-Valenzuela , Samar Hadou , Alejandro Ribeiro

Convolutional neural networks (CNNs) for image processing tend to focus on localized texture patterns, commonly referred to as texture bias. While most of the previous works in the literature focus on the task of image classification, we go…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Edgar Heinert , Matthias Rottmann , Kira Maag , Karsten Kahl

Modern deep learning is primarily an experimental science, in which empirical advances occasionally come at the expense of probabilistic rigor. Here we focus on one such example; namely the use of the categorical cross-entropy loss to model…

Machine Learning · Statistics 2020-11-11 Elliott Gordon-Rodriguez , Gabriel Loaiza-Ganem , Geoff Pleiss , John P. Cunningham

We propose a method for reducing the spatial discretization error of coarse computational fluid dynamics (CFD) problems by enhancing the quality of low-resolution simulations using deep learning. We feed the model with fine-grid data after…

Machine Learning · Computer Science 2024-09-27 Jesus Gonzalez-Sieiro , David Pardo , Vincenzo Nava , Victor M. Calo , Markus Towara

Latent categorical variables are frequently found in deep learning architectures. They can model actions in discrete reinforcement-learning environments, represent categories in latent-variable models, or express relations in graph neural…

Machine Learning · Computer Science 2026-05-14 Alessandro Manenti , Cesare Alippi

Face recognition has made extraordinary progress owing to the advancement of deep convolutional neural networks (CNNs). The central task of face recognition, including face verification and identification, involves face feature…

Computer Vision and Pattern Recognition · Computer Science 2018-04-04 Hao Wang , Yitong Wang , Zheng Zhou , Xing Ji , Dihong Gong , Jingchao Zhou , Zhifeng Li , Wei Liu

Inverse modeling for the estimation of non-Gaussian hydraulic conductivity fields in subsurface flow and solute transport models remains a challenging problem. This is mainly due to the non-Gaussian property, the non-linear physics, and the…

Computational Physics · Physics 2021-03-23 Shaoxing Mo , Nicholas Zabaras , Xiaoqing Shi , Jichun Wu

Owing to security implications of adversarial vulnerability, adversarial robustness of deep metric learning models has to be improved. In order to avoid model collapse due to excessively hard examples, the existing defenses dismiss the…

Machine Learning · Computer Science 2022-03-04 Mo Zhou , Vishal M. Patel

A persistent structural weakness in deep clustering is the disconnect between feature learning and cluster assignment. Most architectures invoke an external clustering step, typically k-means, to produce pseudo-labels that guide training,…

Machine Learning · Computer Science 2026-04-03 Giansalvo Cirrincione

One of the pursued objectives of deep learning is to provide tools that learn abstract representations of reality from the observation of multiple contextual situations. More precisely, one wishes to extract disentangled representations…

Machine Learning · Computer Science 2023-10-24 Pierre Colombo , Nathan Noiry , Guillaume Staerman , Pablo Piantanida

For a widely-studied data model and general loss and sample-hardening functions we prove that the losses of Supervised Contrastive Learning (SCL), Hard-SCL (HSCL), and Unsupervised Contrastive Learning (UCL) are minimized by representations…

Machine Learning · Computer Science 2025-05-08 Ruijie Jiang , Thuan Nguyen , Shuchin Aeron , Prakash Ishwar

Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be tackled by solving a linear least-square problem, which can be done by finding the eigenvector…

Computer Vision and Pattern Recognition · Computer Science 2020-04-20 Zheng Dang , Kwang Moo Yi , Yinlin Hu , Fei Wang , Pascal Fua , Mathieu Salzmann

Local entropic loss functions provide a versatile framework to define architecture-aware regularization procedures. Besides the possibility of being anisotropic in the synaptic space, the local entropic smoothening of the loss function can…

Disordered Systems and Neural Networks · Physics 2021-07-29 Daniele Musso

We introduce the ``soft Deep MaxPain'' (softDMP) algorithm, which integrates the optimization of long-term policy entropy into reward-punishment reinforcement learning objectives. Our motivation is to facilitate a smoother variation of…

Machine Learning · Computer Science 2024-09-16 Jiexin Wang , Eiji Uchibe

Parallelization framework has become a necessity to speed up the training of deep neural networks (DNN) recently. Such framework typically employs the Model Average approach, denoted as MA-DNN, in which parallel workers conduct respective…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-07-19 Shizhao Sun , Wei Chen , Jiang Bian , Xiaoguang Liu , Tie-Yan Liu

The softmax cross-entropy loss function has been widely used to train deep models for various tasks. In this work, we propose a Gaussian mixture (GM) loss function for deep neural networks for visual classification. Unlike the softmax…

Computer Vision and Pattern Recognition · Computer Science 2020-11-19 Weitao Wan , Jiansheng Chen , Cheng Yu , Tong Wu , Yuanyi Zhong , Ming-Hsuan Yang

Implicit regularization is an important way to interpret neural networks. Recent theory starts to explain implicit regularization with the model of deep matrix factorization (DMF) and analyze the trajectory of discrete gradient dynamics in…

Machine Learning · Computer Science 2023-08-14 Jian Cao , Chen Qian , Yihui Huang , Dicheng Chen , Yuncheng Gao , Jiyang Dong , Di Guo , Xiaobo Qu

Deep neural networks are workhorse models in machine learning with multiple layers of non-linear functions composed in series. Their loss function is highly non-convex, yet empirically even gradient descent minimisation is sufficient to…

Disordered Systems and Neural Networks · Physics 2020-03-18 Simon Becker , Yao Zhang , Alpha A. Lee

The optimization of deep neural networks can be more challenging than traditional convex optimization problems due to the highly non-convex nature of the loss function, e.g. it can involve pathological landscapes such as saddle-surfaces…

Machine Learning · Computer Science 2016-08-18 Caglar Gulcehre , Marcin Moczulski , Francesco Visin , Yoshua Bengio