English
Related papers

Related papers: Understanding over-parameterized deep networks by …

200 papers

We propose to impose symmetry in neural network parameters to improve parameter usage and make use of dedicated convolution and matrix multiplication routines. Due to significant reduction in the number of parameters as a result of the…

Machine Learning · Computer Science 2019-01-11 Xu Shell Hu , Sergey Zagoruyko , Nikos Komodakis

There have been several attempts to mathematically understand neural networks and many more from biological and computational perspectives. The field has exploded in the last decade, yet neural networks are still treated much like a black…

Neural and Evolutionary Computing · Computer Science 2016-12-09 Sven Cattell

In this work, we develop new generalization bounds for neural networks trained on data supported on Riemannian manifolds. Existing generalization theories often rely on complexity measures derived from Euclidean geometry, which fail to…

Machine Learning · Computer Science 2025-07-08 Krisanu Sarkar

Thanks to the availability of large scale digital datasets and massive amounts of computational power, deep learning algorithms can learn representations of data by exploiting multiple levels of abstraction. These machine learning methods…

Disordered Systems and Neural Networks · Physics 2018-10-01 Alberto Testolin , Michele Piccolini , Samir Suweis

This paper addresses the challenges of designing mesh convolution neural networks for 3D mesh dense prediction. While deep learning has achieved remarkable success in image dense prediction tasks, directly applying or extending these…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Shi Hezi , Jiang Luo , Zheng Jianmin , Zeng Jun

In the wake of the growing popularity of machine learning in particle physics, this work finds a new application of geometric deep learning on Feynman diagrams to make accurate and fast matrix element predictions with the potential to be…

Computational Physics · Physics 2022-11-29 Harrison Mitchell , Alexander Norcliffe , Pietro Liò

This work provides a theoretical framework for assessing the generalization error of graph neural networks in the over-parameterized regime, where the number of parameters surpasses the quantity of data points. We explore two widely…

Machine Learning · Statistics 2024-07-02 Gholamali Aminian , Yixuan He , Gesine Reinert , Łukasz Szpruch , Samuel N. Cohen

The skip-connections used in residual networks have become a standard architecture choice in deep learning due to the increased training stability and generalization performance with this architecture, although there has been limited…

Machine Learning · Computer Science 2019-10-08 Spencer Frei , Yuan Cao , Quanquan Gu

In over-parameterized deep neural networks there can be many possible parameter configurations that fit the training data exactly. However, the properties of these interpolating solutions are poorly understood. We argue that…

Machine Learning · Computer Science 2021-12-02 Benoit Dherin , Michael Munn , David G. T. Barrett

Geometric deep learning has recently achieved great success in non-Euclidean domains, and learning on 3D structures of large biomolecules is emerging as a distinct research area. However, its efficacy is largely constrained due to the…

Machine Learning · Computer Science 2023-10-31 Fang Wu , Lirong Wu , Dragomir Radev , Jinbo Xu , Stan Z. Li

Analysis of over-parameterized neural networks has drawn significant attention in recentyears. It was shown that such systems behave like convex systems under various restrictedsettings, such as for two-level neural networks, and when…

Machine Learning · Computer Science 2019-11-19 Cong Fang , Yihong Gu , Weizhong Zhang , Tong Zhang

Deep learning is a broad set of techniques that uses multiple layers of representation to automatically learn relevant features directly from structured data. Recently, such techniques have yielded record-breaking results on a diverse set…

Machine Learning · Statistics 2014-10-16 Pankaj Mehta , David J. Schwab

Riemannian geometry is a mathematical field which has been the cornerstone of revolutionary scientific discoveries such as the theory of general relativity. Despite early uses in robot design and recent applications for exploiting data with…

Robotics · Computer Science 2022-10-03 Noémie Jaquier , Tamim Asfour

One of the central problems in the interface of deep learning and mathematics is that of building learning systems that can automatically uncover underlying mathematical laws from observed data. In this work, we make one step towards…

Machine Learning · Computer Science 2021-02-15 Mustafa Hajij , Ghada Zamzmi , Matthew Dawson , Greg Muller

The primary objective of learning methods is generalization. Classic uniform generalization bounds, which rely on VC-dimension or Rademacher complexity, fail to explain the significant attribute that over-parameterized models in deep…

Machine Learning · Computer Science 2025-03-07 Lijia Yu , Yibo Miao , Yifan Zhu , Xiao-Shan Gao , Lijun Zhang

We consider the problem of training a deep orthogonal linear network, which consists of a product of orthogonal matrices, with no non-linearity in-between. We show that training the weights with Riemannian gradient descent is equivalent to…

Machine Learning · Statistics 2020-11-30 Pierre Ablin

Artificial neural networks (ANNs) are powerful tools capable of approximating any arbitrary mathematical function, but their interpretability remains limited, rendering them as black box models. To address this issue, numerous methods have…

Machine Learning · Computer Science 2024-06-11 Abhiram Anand Thiruthummal , Eun-jin Kim , Sergiy Shelyag

This work describes how the formalization of complex network concepts in terms of discrete mathematics, especially mathematical morphology, allows a series of generalizations and important results ranging from new measurements of the…

Statistical Mechanics · Physics 2007-09-19 Luciano da Fontoura Costa , Luis Enrique C. da Rocha

Real networks often form interacting parts of larger and more complex systems. Examples can be found in different domains, ranging from the Internet to structural and functional brain networks. Here, we show that these multiplex systems are…

Physics and Society · Physics 2017-09-11 Kaj-Kolja Kleineberg , Marian Boguna , M. Angeles Serrano , Fragkiskos Papadopoulos

In all but the most trivial optimization problems, the structure of the solutions exhibit complex interdependencies between the input parameters. Decades of research with stochastic search techniques has shown the benefit of explicitly…

Neural and Evolutionary Computing · Computer Science 2017-03-23 Shumeet Baluja
‹ Prev 1 4 5 6 7 8 10 Next ›