English
Related papers

Related papers: Partial local entropy and anisotropy in deep weigh…

200 papers

Loss functions are error metrics that quantify the difference between a prediction and its corresponding ground truth. Fundamentally, they define a functional landscape for traversal by gradient descent. Although numerous loss functions…

Image and Video Processing · Electrical Eng. & Systems 2021-04-09 Chaitanya Kaul , Nick Pears , Hang Dai , Roderick Murray-Smith , Suresh Manandhar

For fixed training data and network parameters in the other layers the L1 loss of a ReLU neural network as a function of the first layer's parameters is a piece-wise affine function. We use the Deep ReLU Simplex algorithm to iteratively…

Machine Learning · Statistics 2021-05-07 Peter Hinz

For a large class of feature maps we provide a tight asymptotic characterisation of the test error associated with learning the readout layer, in the high-dimensional limit where the input dimension, hidden layer widths, and number of…

Machine Learning · Statistics 2024-06-11 Dominik Schröder , Daniil Dmitriev , Hugo Cui , Bruno Loureiro

Since their introduction, Transformer architectures have dominated Natural Language Processing (NLP). However, recent research has highlighted an inherent anisotropy phenomenon in these models, presenting a significant challenge to their…

Computation and Language · Computer Science 2026-04-13 Raphael Bernas , Fanny Jourdan , Antonin Poché , Céline Hudelot

There has been a lot of recent interest in trying to characterize the error surface of deep models. This stems from a long standing question. Given that deep networks are highly nonlinear systems optimized by local gradient methods, why do…

Machine Learning · Statistics 2017-02-20 Grzegorz Swirszcz , Wojciech Marian Czarnecki , Razvan Pascanu

An usual problem in statistics consists in estimating the minimizer of a convex function. When we have to deal with large samples taking values in high dimensional spaces, stochastic gradient algorithms and their averaged versions are…

Statistics Theory · Mathematics 2022-01-12 Antoine Godichon-Baggioni

We explore the potential for using a nonsmooth loss function based on the max-norm in the training of an artificial neural network. We hypothesise that this may lead to superior classification results in some special cases where the…

Machine Learning · Computer Science 2021-07-20 Vinesha Peiris , Nadezda Sukhorukova , Vera Roshchina

This paper is the first attempt to use geometric deep learning and Sobolev training to incorporate non-Euclidean microstructural data such that anisotropic hyperelastic material machine learning models can be trained in the finite…

Machine Learning · Computer Science 2020-10-12 Nikolaos Vlassis , Ran Ma , WaiChing Sun

We introduce directional regularity, a new definition of anisotropy for multivariate functional data. Instead of taking the conventional view, which determines anisotropy as a notion of smoothness along a dimension, directional regularity…

Methodology · Statistics 2026-05-05 Omar Kassi , Sunny G. W. Wang

Deep learning has been shown to achieve impressive results in several domains like computer vision and natural language processing. A key element of this success has been the development of new loss functions, like the popular cross-entropy…

Machine Learning · Computer Science 2019-07-19 Francesco Giannini , Giuseppe Marra , Michelangelo Diligenti , Marco Maggini , Marco Gori

A deep learning framework is developed for multiscale characterization of poroelastic media from full waveform data which is known as poroelastography. Special attention is paid to heterogeneous environments whose multiphase properties may…

Signal Processing · Electrical Eng. & Systems 2024-11-15 Yang Xu , Fatemeh Pourahmadian

In this paper we consider a class of non-local in time telegraph equations. Recently, it has been proved that the fundamental solutions of such equations can be interpreted as the probability density function of a stochastic process. We…

Analysis of PDEs · Mathematics 2021-01-20 Francisco Alegría , Juan C. Pozo

Learned image compression methods have attracted great research interest and exhibited superior rate-distortion performance to the best classical image compression standards of the present. The entropy model plays a key role in learned…

Computer Vision and Pattern Recognition · Computer Science 2025-05-16 Jingbo Lu , Leheng Zhang , Xingyu Zhou , Mu Li , Wen Li , Shuhang Gu

Ground texture based localization methods are potential prospects for low-cost, high-accuracy self-localization solutions for robots. These methods estimate the pose of a given query image, i.e. the current observation of the ground from a…

Computer Vision and Pattern Recognition · Computer Science 2021-09-06 Raaghav Radhakrishnan , Jan Fabian Schmid , Randolf Scholz , Lars Schmidt-Thieme

Continuous neural representations have recently emerged as a powerful and flexible alternative to classical discretized representations of signals. However, training them to capture fine details in multi-scale signals is difficult and…

Machine Learning · Computer Science 2022-10-06 Sifan Wang , Hanwen Wang , Jacob H. Seidman , Paris Perdikaris

Deep Learning has become interestingly popular in computer vision, mostly attaining near or above human-level performance in various vision tasks. But recent work has also demonstrated that these deep neural networks are very vulnerable to…

Machine Learning · Computer Science 2020-12-09 Shashi Kant Gupta

A recent line of research has shown that gradient-based algorithms with random initialization can converge to the global minima of the training loss for over-parameterized (i.e., sufficiently wide) deep neural networks. However, the…

Machine Learning · Computer Science 2019-06-12 Difan Zou , Quanquan Gu

The function space of deep-learning machines is investigated by studying growth in the entropy of functions of a given error with respect to a reference function, realized by a deep-learning machine. Using physics-inspired methods we study…

Disordered Systems and Neural Networks · Physics 2018-08-10 Bo Li , David Saad

Two aspects of neural networks that have been extensively studied in the recent literature are their function approximation properties and their training by gradient descent methods. The approximation problem seeks accurate approximations…

Machine Learning · Computer Science 2022-09-20 R. Gentile , G. Welper

In deep multi-task learning, weights of task-specific networks are shared between tasks to improve performance on each single one. Since the question, which weights to share between layers, is difficult to answer, human-designed…

Machine Learning · Computer Science 2020-03-24 Jonas Prellberg , Oliver Kramer
‹ Prev 1 3 4 5 6 7 10 Next ›