English
Related papers

Related papers: When Do Neural Networks Outperform Kernel Methods?

200 papers

We develop a stochastic approximation framework for learning nonlinear operators between infinite-dimensional spaces utilizing general Mercer operator-valued kernels. Our framework encompasses two key classes: (i) compact kernels, which…

Machine Learning · Statistics 2026-01-13 Jia-Qi Yang , Lei Shi

This paper investigates the connection between neural networks and sufficient dimension reduction (SDR), demonstrating that neural networks inherently perform SDR in regression tasks under appropriate rank regularizations. Specifically, the…

Machine Learning · Statistics 2024-12-30 Shuntuo Xu , Zhou Yu

We describe the class of convexified convolutional neural networks (CCNNs), which capture the parameter sharing of convolutional neural networks in a convex manner. By representing the nonlinear convolutional filters as vectors in a…

Machine Learning · Computer Science 2016-09-06 Yuchen Zhang , Percy Liang , Martin J. Wainwright

For certain infinitely-wide neural networks, the neural tangent kernel (NTK) theory fully characterizes generalization, but for the networks used in practice, the empirical NTK only provides a rough first-order approximation. Still, a…

Machine Learning · Computer Science 2021-10-14 Guillermo Ortiz-Jiménez , Seyed-Mohsen Moosavi-Dezfooli , Pascal Frossard

Deep kernel learning aims at designing nonlinear combinations of multiple standard elementary kernels by training deep networks. This scheme has proven to be effective, but intractable when handling large-scale datasets especially when the…

Computer Vision and Pattern Recognition · Computer Science 2018-05-01 Mingyuan Jiu , Hichem Sahbi

Deep Neural Networks (DNNs) training can be difficult due to vanishing and exploding gradients during weight optimization through backpropagation. To address this problem, we propose a general class of Hamiltonian DNNs (H-DNNs) that stem…

Machine Learning · Computer Science 2023-01-02 Clara Lucía Galimberti , Luca Furieri , Liang Xu , Giancarlo Ferrari-Trecate

Recent empirical work has shown that hierarchical convolutional kernels inspired by convolutional neural networks (CNNs) significantly improve the performance of kernel methods in image classification tasks. A widely accepted explanation…

Machine Learning · Statistics 2022-06-06 Theodor Misiakiewicz , Song Mei

We analyze the performance of graph neural network (GNN) architectures from the perspective of random graph theory. Our approach promises to complement existing lenses on GNN analysis, such as combinatorial expressive power and worst-case…

Machine Learning · Computer Science 2023-10-12 Drake Brown , Trevor Garrity , Kaden Parker , Jason Oliphant , Stone Carson , Cole Hanson , Zachary Boyd

Many supervised learning tasks have intrinsic symmetries, such as translational and rotational symmetry in image classifications. These symmetries can be exploited to enhance performance. We formulate the symmetry constraints into a concise…

Quantum Physics · Physics 2024-08-14 Kaiming Bian , Shitao Zhang , Fei Meng , Wen Zhang , Oscar Dahlsten

Deep neural networks have exhibited remarkable performance in image super-resolution (SR) tasks by learning a mapping from low-resolution (LR) images to high-resolution (HR) images. However, the SR problem is typically an ill-posed problem…

Computer Vision and Pattern Recognition · Computer Science 2024-05-29 Yong Guo , Mingkui Tan , Zeshuai Deng , Jingdong Wang , Qi Chen , Jiezhang Cao , Yanwu Xu , Jian Chen

Learning in Deep Neural Networks (DNN) takes place by minimizing a non-convex high-dimensional loss function, typically by a stochastic gradient descent (SGD) strategy. The learning process is observed to be able to find good minimizers…

Machine Learning · Computer Science 2020-03-12 Carlo Baldassi , Fabrizio Pittorino , Riccardo Zecchina

In this paper, we propose a novel kernel stochastic gradient descent (SGD) algorithm for large-scale supervised learning with general losses. Compared to traditional kernel SGD, our algorithm improves efficiency and scalability through an…

Machine Learning · Computer Science 2026-04-28 Jinhui Bai , Andreas Christmann , Lei Shi

We rigorously study the relation between the training dynamics via stochastic gradient descent (SGD) and the spectra of empirical Hessian and gradient matrices. We prove that in two canonical classification tasks for multi-class…

Machine Learning · Computer Science 2025-05-19 Gerard Ben Arous , Reza Gheissari , Jiaoyang Huang , Aukosh Jagannath

This study compares various superlearner and deep learning architectures (machine-learning-based and neural-network-based) for classification problems across several simulated and industrial datasets to assess performance and computational…

Machine Learning · Statistics 2017-08-23 Colleen M. Farrelly

Large-scale distributed training of deep neural networks results in models with worse generalization performance as a result of the increase in the effective mini-batch size. Previous approaches attempt to address this problem by varying…

Machine Learning · Computer Science 2020-02-17 Kazuki Osawa , Yohei Tsuji , Yuichiro Ueno , Akira Naruse , Chuan-Sheng Foo , Rio Yokota

We present a novel diffusion scheme for online kernel-based learning over networks. So far, a major drawback of any online learning algorithm, operating in a reproducing kernel Hilbert space (RKHS), is the need for updating a growing number…

Machine Learning · Computer Science 2018-03-14 Pantelis Bouboulis , Symeon Chouvardas , Sergios Theodoridis

Recursive least squares (RLS) algorithms were once widely used for training small-scale neural networks, due to their fast convergence. However, previous RLS algorithms are unsuitable for training deep neural networks (DNNs), since they…

Machine Learning · Computer Science 2021-09-08 Chunyuan Zhang , Qi Song , Hui Zhou , Yigui Ou , Hongyao Deng , Laurence Tianruo Yang

This paper proposes a method for constructing one-step prediction tubes for nonlinear systems using reproducing kernel Hilbert spaces. We approximate a bounded reproducing kernel Hilbert space (RKHS) hypothesis set by a finite-dimensional…

Systems and Control · Electrical Eng. & Systems 2026-04-08 Jannis Lübsen , Annika Eichler

Deep neural networks for image super-resolution (SR) have demonstrated superior performance. However, the large memory and computation consumption hinders their deployment on resource-constrained devices. Binary neural networks (BNNs),…

Computer Vision and Pattern Recognition · Computer Science 2025-02-24 Renjie Wei , Zechun Liu , Yuchen Fan , Runsheng Wang , Ru Huang , Meng Li

Several recent trends in machine learning theory and practice, from the design of state-of-the-art Gaussian Process to the convergence analysis of deep neural nets (DNNs) under stochastic gradient descent (SGD), have found it fruitful to…

Neural and Evolutionary Computing · Computer Science 2020-04-07 Greg Yang