English
Related papers

Related papers: Locality defeats the curse of dimensionality in co…

200 papers

How many training data are needed to learn a supervised task? It is often observed that the generalization error decreases as $n^{-\beta}$ where $n$ is the number of training examples and $\beta$ an exponent that depends on both data and…

Machine Learning · Statistics 2021-02-03 Stefano Spigler , Mario Geiger , Matthieu Wyart

We study feature learning in a compositional variant of kernel ridge regression in which the predictor is applied to a learnable linear transformation of the input. When the response depends on the input only through a low-dimensional…

Statistics Theory · Mathematics 2026-02-17 Yunlu Chen , Yang Li , Keli Liu , Feng Ruan

We investigate how the training curve of isotropic kernel methods depends on the symmetry of the task to be learned, in several settings. (i) We consider a regression task, where the target function is a Gaussian random field that depends…

Machine Learning · Computer Science 2020-12-16 Jonas Paccolat , Stefano Spigler , Matthieu Wyart

Ridgeless regression has garnered attention among researchers, particularly in light of the ``Benign Overfitting'' phenomenon, where models interpolating noisy samples demonstrate robust generalization. However, kernel ridgeless regression…

Machine Learning · Computer Science 2024-06-04 Fan He , Mingzhen He , Lei Shi , Xiaolin Huang , Johan A. K. Suykens

Recent theoretical studies illustrated that kernel ridgeless regression can guarantee good generalization ability without an explicit regularization. In this paper, we investigate the statistical properties of ridgeless regression with…

Machine Learning · Computer Science 2023-08-30 Jian Li , Yong Liu , Yingying Zhang

Training dataset biases are by far the most scrutinized factors when explaining algorithmic biases of neural networks. In contrast, hyperparameters related to the neural network architecture have largely been ignored even though different…

Computer Vision and Pattern Recognition · Computer Science 2023-12-05 Hao Liang , Josue Ortega Caro , Vikram Maheshri , Ankit B. Patel , Guha Balakrishnan

The huge amount of available data nowadays is a challenge for kernel-based machine learning algorithms like SVMs with respect to runtime and storage capacities. Local approaches might help to relieve these issues and to improve statistical…

Machine Learning · Statistics 2019-03-05 Florian Dumpert

This paper studies an intriguing phenomenon related to the good generalization performance of estimators obtained by using large learning rates within gradient descent algorithms. First observed in the deep learning literature, we show that…

Machine Learning · Statistics 2022-06-06 Gaspard Beugnot , Julien Mairal , Alessandro Rudi

We study the learning properties of nonparametric ridge-less least squares. In particular, we consider the common case of estimators defined by scale dependent kernels, and focus on the role of the scale. These estimators interpolate the…

Machine Learning · Statistics 2021-11-11 Nicolò Pagliana , Alessandro Rudi , Ernesto De Vito , Lorenzo Rosasco

The lack of sufficient flexibility is the key bottleneck of kernel-based learning that relies on manually designed, pre-given, and non-trainable kernels. To enhance kernel flexibility, this paper introduces the concept of…

Machine Learning · Computer Science 2023-10-10 Fan He , Mingzhen He , Lei Shi , Xiaolin Huang , Johan A. K. Suykens

Over-parameterized models like deep nets and random forests have become very popular in machine learning. However, the natural goals of continuity and differentiability, common in regression models, are now often ignored in modern…

Machine Learning · Computer Science 2023-10-16 Mingxuan Han , Varun Shankar , Jeff M Phillips , Chenglong Ye

Regression neural networks (NNs) are most commonly trained by minimizing the mean squared prediction error, which is highly sensitive to outliers and data contamination. Existing robust training methods for regression NNs are often limited…

Machine Learning · Statistics 2026-02-10 Abhik Ghosh , Suryasis Jana

We consider the problem of learning a linear operator $\theta$ between two Hilbert spaces from empirical observations, which we interpret as least squares regression in infinite dimensions. We show that this goal can be reformulated as an…

Statistics Theory · Mathematics 2024-07-11 Mattes Mollenhauer , Nicole Mücke , T. J. Sullivan

A number of machine learning tasks entail a high degree of invariance: the data distribution does not change if we act on the data with a certain group of transformations. For instance, labels of images are invariant under translations of…

Machine Learning · Statistics 2021-03-01 Song Mei , Theodor Misiakiewicz , Andrea Montanari

This paper presents a phenomenon in neural networks that we refer to as \textit{local elasticity}. Roughly speaking, a classifier is said to be locally elastic if its prediction at a feature vector $\bx'$ is \textit{not} significantly…

Machine Learning · Computer Science 2020-02-18 Hangfeng He , Weijie J. Su

Metric and kernel learning are important in several machine learning applications. However, most existing metric learning algorithms are limited to learning metrics over low-dimensional data, while existing kernel learning algorithms are…

Machine Learning · Computer Science 2009-11-02 Prateek Jain , Brian Kulis , Jason V. Davis , Inderjit S. Dhillon

Convolutional Neural Networks (ConvNets) have shown excellent results on many visual classification tasks. With the exception of ImageNet, these datasets are carefully crafted such that objects are well-aligned at similar scales. Naturally,…

Computer Vision and Pattern Recognition · Computer Science 2014-12-17 Angjoo Kanazawa , Abhishek Sharma , David Jacobs

The choice of the kernel is critical to the success of many learning algorithms but it is typically left to the user. Instead, the training data can be used to learn the kernel by selecting it out of a given family, such as that of…

Machine Learning · Computer Science 2012-05-14 Corinna Cortes , Mehryar Mohri , Afshin Rostamizadeh

One of the main drawbacks of the practical use of neural networks is the long time required in the training process. Such a training process consists of an iterative change of parameters trying to minimize a loss function. These changes are…

Machine Learning · Computer Science 2024-03-14 Rocio Gonzalez-Diaz , Miguel A. Gutiérrez-Naranjo , Eduardo Paluzo-Hidalgo

We consider the problem of learning convolution operators associated to compact Abelian groups. We study a regularization-based approach and provide corresponding learning guarantees under natural regularity conditions on the convolution…

Machine Learning · Computer Science 2025-04-11 Emilia Magnani , Ernesto De Vito , Philipp Hennig , Lorenzo Rosasco
‹ Prev 1 2 3 10 Next ›