English
Related papers

Related papers: Entropic alternatives to initialization

200 papers

The role of $L^2$ regularization, in the specific case of deep neural networks rather than more traditional machine learning models, is still not fully elucidated. We hypothesize that this complex interplay is due to the combination of…

Machine Learning · Computer Science 2019-02-11 Pierre H. Richemond , Yike Guo

Learning embeddings from large-scale networks is an open challenge. Despite the overwhelming number of existing methods, is is unclear how to exploit network structure in a way that generalizes easily to unseen nodes, edges or graphs. In…

Machine Learning · Computer Science 2020-09-29 Nurudin Alvarez-Gonzalez , Andreas Kaltenbrunner , Vicenç Gómez

Advancements in parallel processing have lead to a surge in multilayer perceptrons' (MLP) applications and deep learning in the past decades. Recurrent Neural Networks (RNNs) give additional representational power to feedforward MLPs by…

Machine Learning · Statistics 2014-10-22 Saahil Ognawala , Justin Bayer

Standard neural network architectures are non-linear only by virtue of a simple element-wise activation function, making them both brittle and excessively large. In this paper, we consider methods for making the feed-forward layer more…

Machine Learning · Computer Science 2018-11-26 Sebastian Flennerhag , Hujun Yin , John Keane , Mark Elliot

Inhomogeneities in real-world data, e.g., due to changes in the observation noise level or variations in the structural complexity of the source function, pose a unique set of challenges for statistical inference. Accounting for them can…

Machine Learning · Computer Science 2023-12-13 Danny Panknin , Stefan Chmiela , Klaus-Robert Müller , Shinichi Nakajima

Deep neural networks possess strong representational capacity yet remain vulnerable to overfitting, primarily because neurons tend to co-adapt in ways that, while capturing complex and fine-grained feature interactions, also reinforce…

Machine Learning · Computer Science 2025-12-16 Gelesh G Omathil , Sreeja CS

In this paper we discuss a well known computing problem -- inference for models with intractable normalizing functions. Models with intractable normalizing functions arise in a wide variety of areas, for instance network models, models for…

Methodology · Statistics 2026-03-19 Murali Haran , Bokgyeong Kang , Jaewoo Park

The strength of machine learning models stems from their ability to learn complex function approximations from data; however, this strength also makes training deep neural networks challenging. Notably, the complex models tend to memorize…

Computer Vision and Pattern Recognition · Computer Science 2023-04-17 Mofassir ul Islam Arif , Mohsan Jameel , Josif Grabocka , Lars Schmidt-Thieme

We study the compact embedding between smoothness Morrey spaces on bounded domains and characterise its entropy numbers. Here we discover a new phenomenon when the difference of smoothness parameters in the source and target spaces is…

Functional Analysis · Mathematics 2020-04-22 Dorothee D. Haroske , Leszek Skrzypczak

We introduce a paradigm for nonlocal sparsity reinforced deep convolutional neural network denoising. It is a combination of a local multiscale denoising by a convolutional neural network (CNN) based denoiser and a nonlocal denoising based…

Image and Video Processing · Electrical Eng. & Systems 2018-08-15 Cristóvão Cruz , Alessandro Foi , Vladimir Katkovnik , Karen Egiazarian

Using established principles from Statistics and Information Theory, we show that invariance to nuisance factors in a deep neural network is equivalent to information minimality of the learned representation, and that stacking layers and…

Machine Learning · Computer Science 2018-06-29 Alessandro Achille , Stefano Soatto

While variational methods have been among the most powerful tools for solving linear inverse problems in imaging, deep (convolutional) neural networks have recently taken the lead in many challenging benchmarks. A remaining drawback of deep…

Computer Vision and Pattern Recognition · Computer Science 2019-08-20 Tim Meinhardt , Michael Moeller , Caner Hazirbas , Daniel Cremers

The cross-entropy loss commonly used in deep learning is closely related to the defining properties of optimal representations, but does not enforce some of the key properties. We show that this can be solved by adding a regularization…

Machine Learning · Statistics 2017-02-14 Alessandro Achille , Stefano Soatto

In this paper, we develop upon the emerging topic of loss function learning, which aims to learn loss functions that significantly improve the performance of the models trained under them. Specifically, we propose a new meta-learning…

Machine Learning · Computer Science 2024-07-02 Christian Raymond , Qi Chen , Bing Xue , Mengjie Zhang

We present a general variational framework for the training of freeform nonlinearities in layered computational architectures subject to some slope constraints. The regularization that we add to the traditional training loss penalizes the…

Machine Learning · Statistics 2025-03-31 Michael Unser , Alexis Goujon , Stanislas Ducotterd

Recent end-to-end deep neural networks for disparity regression have achieved the state-of-the-art performance. However, many well-acknowledged specific properties of disparity estimation are omitted in these deep learning algorithms.…

Computer Vision and Pattern Recognition · Computer Science 2020-05-29 Yang Chen , Zongqing Lu , Xuechen Zhang , Lei Chen , Qingmin Liao

Deep learning has powered recent successes of artificial intelligence (AI). However, the deep neural network, as the basic model of deep learning, has suffered from issues such as local traps and miscalibration. In this paper, we provide a…

Machine Learning · Statistics 2021-12-03 Yan Sun , Wenjun Xiong , Faming Liang

Due to its geometric properties, hyperbolic space can support high-fidelity embeddings of tree- and graph-structured data, upon which various hyperbolic networks have been developed. Existing hyperbolic networks encode geometric priors not…

Machine Learning · Computer Science 2023-03-14 Tao Yu , Christopher De Sa

Neural networks are more expressive when they have multiple layers. In turn, conventional training methods are only successful if the depth does not lead to numerical issues such as exploding or vanishing gradients, which occur less…

Machine Learning · Computer Science 2022-06-07 Carles Riera , Camilo Rey , Thiago Serra , Eloi Puertas , Oriol Pujol

We propose a complement to constitutive modeling that augments neural networks with material principles to capture anisotropy and inelasticity at finite strains. The key element is a dual potential that governs dissipation, consistently…

Computational Engineering, Finance, and Science · Computer Science 2025-12-09 Hagen Holthusen , Ellen Kuhl
‹ Prev 1 3 4 5 6 7 10 Next ›