English
Related papers

Related papers: On the Benefits of Large Learning Rates for Kernel…

200 papers

Robustness and resource-efficiency are two highly desirable properties for modern machine learning models. However, achieving them jointly remains a challenge. In this paper, we identify high learning rates as a facilitator for…

Machine Learning · Computer Science 2025-08-06 Melih Barsbey , Lucas Prieto , Stefanos Zafeiriou , Tolga Birdal

Most theoretical studies explaining the regularization effect in deep learning have only focused on gradient descent with a sufficient small learning rate or even gradient flow (infinitesimal learning rate). Such researches, however, have…

Machine Learning · Computer Science 2020-12-17 Wei Huang , Weitao Du , Richard Yi Da Xu , Chunrui Liu

Learning kernels in operators from data lies at the intersection of inverse problems and statistical learning, providing a powerful framework for capturing non-local dependencies in function spaces and high-dimensional settings. In contrast…

Statistics Theory · Mathematics 2025-06-24 Sichong Zhang , Xiong Wang , Fei Lu

Distributed learning is an effective way to analyze big data. In distributed regression, a typical approach is to divide the big data into multiple blocks, apply a base regression algorithm on each of them, and then simply average the…

Machine Learning · Computer Science 2017-08-08 Zhengchu Guo , Lei Shi , Qiang Wu

We develop a new theoretical framework to analyze the generalization error of deep learning, and derive a new fast learning rate for two representative algorithms: empirical risk minimization and Bayesian deep learning. The series of…

Statistics Theory · Mathematics 2017-05-31 Taiji Suzuki

Additive models play an important role in semiparametric statistics. This paper gives learning rates for regularized kernel based methods for additive models. These learning rates compare favourably in particular in high dimensions to…

Machine Learning · Statistics 2014-05-15 Andreas Christmann , Ding-Xuan Zhou

Randomly initialized first-order optimization algorithms are the method of choice for solving many high-dimensional nonconvex problems in machine learning, yet general theoretical guarantees cannot rule out convergence to critical points of…

Optimization and Control · Mathematics 2018-09-28 Dar Gilboa , Sam Buchanan , John Wright

Random feature approximation is arguably one of the most widely used techniques for kernel methods in large-scale learning algorithms. In this work, we analyze the generalization properties of random feature methods, extending previous…

Machine Learning · Statistics 2025-06-23 Mike Nguyen , Nicole Mücke

A recent series of theoretical works showed that the dynamics of neural networks with a certain initialisation are well-captured by kernel methods. Concurrent empirical work demonstrated that kernel methods can come close to the performance…

Machine Learning · Computer Science 2021-06-11 Maria Refinetti , Sebastian Goldt , Florent Krzakala , Lenka Zdeborová

A well-recognized limitation of kernel learning is the requirement to handle a kernel matrix, whose size is quadratic in the number of training examples. Many methods have been proposed to reduce this computational cost, mostly by using a…

Machine Learning · Computer Science 2014-11-06 Nicolò Cesa-Bianchi , Yishay Mansour , Ohad Shamir

It is generally accepted that starting neural networks training with large learning rates (LRs) improves generalization. Following a line of research devoted to understanding this effect, we conduct an empirical study in a controlled…

Machine Learning · Computer Science 2024-10-30 Ildus Sadrtdinov , Maxim Kodryan , Eduard Pokonechny , Ekaterina Lobacheva , Dmitry Vetrov

Stochastic gradient descent algorithms for training linear and kernel predictors are gaining more and more importance, thanks to their scalability. While various methods have been proposed to speed up their convergence, the model selection…

Machine Learning · Computer Science 2014-06-17 Francesco Orabona

Near an optimal learning point of a neural network, the learning performance of gradient descent dynamics is dictated by the Hessian matrix of the loss function with respect to the network parameters. We characterize the Hessian…

Machine Learning · Statistics 2025-12-18 Carlos Couto , José Mourão , Mário A. T. Figueiredo , Pedro Ribeiro

This paper proposes a novel kernel approach to linear dimension reduction for supervised learning. The purpose of the dimension reduction is to find directions in the input space to explain the output as effectively as possible. The…

Machine Learning · Statistics 2011-09-05 Kenji Fukumizu , Chenlei Leng

Why do neural networks trained with large learning rates for a longer time often lead to better generalization? In this paper, we delve into this question by examining the relation between training and testing loss in neural networks.…

Machine Learning · Computer Science 2024-01-23 Yinuo Ren , Chao Ma , Lexing Ying

We study generalization properties of kernel regularized least squares regression based on a partitioning approach. We show that optimal rates of convergence are preserved if the number of local sets grows sufficiently slowly with the…

Statistics Theory · Mathematics 2019-02-26 Nicole Mücke

Deep learning's successes are often attributed to its ability to automatically discover new representations of the data, rather than relying on handcrafted features like other learning methods. We show, however, that deep networks learned…

Machine Learning · Computer Science 2020-12-02 Pedro Domingos

Gradient descent and coordinate descent are well understood in terms of their asymptotic behavior, but less so in a transient regime often used for approximations in machine learning. We investigate how proper initialization can have a…

Machine Learning · Computer Science 2017-06-14 Hadi Daneshmand , Hamed Hassani , Thomas Hofmann

Under mild assumptions on the kernel, we obtain the best known error rates in a regularized learning scenario taking place in the corresponding reproducing kernel Hilbert space (RKHS). The main novelty in the analysis is a proof that one…

Statistics Theory · Mathematics 2010-01-14 Shahar Mendelson , Joseph Neeman

Learning rate schedulers have been widely adopted in training deep neural networks. Despite their practical importance, there is a discrepancy between its practice and its theoretical analysis. For instance, it is not known what schedules…

Machine Learning · Computer Science 2022-06-15 Rui Pan , Haishan Ye , Tong Zhang