English
Related papers

Related papers: Random Feature Maps for Dot Product Kernels

200 papers

We analyze in this paper a random feature map based on a theory of invariance I-theory introduced recently. More specifically, a group invariant signal signature is obtained through cumulative distributions of group transformed random…

Machine Learning · Computer Science 2015-12-07 Youssef Mroueh , Stephen Voinea , Tomaso Poggio

The empirical success of deep convolutional networks on tasks involving high-dimensional data such as images or audio suggests that they can efficiently approximate certain functions that are well-suited for such tasks. In this paper, we…

Machine Learning · Statistics 2022-03-22 Alberto Bietti

We introduce a regularization loss based on kernel mean embeddings with rotation-invariant kernels on the hypersphere (also known as dot-product kernels) for self-supervised learning of image representations. Besides being fully competitive…

Computer Vision and Pattern Recognition · Computer Science 2023-03-09 Léon Zheng , Gilles Puy , Elisa Riccietti , Patrick Pérez , Rémi Gribonval

Applications such as face recognition that deal with high-dimensional data need a mapping technique that introduces representation of low-dimensional features with enhanced discriminatory power and a proper classifier, able to classify…

Computer Vision and Pattern Recognition · Computer Science 2008-12-16 Seyyed Majid Valiollahzadeh , Abolghasem Sayadiyan , Mohammad Nazari

Kernel mean embeddings are a popular tool that consists in representing probability measures by their infinite-dimensional mean embeddings in a reproducing kernel Hilbert space. When the kernel is characteristic, mean embeddings can be used…

Machine Learning · Computer Science 2021-06-29 Boris Muzellec , Francis Bach , Alessandro Rudi

Deep classifiers are known to rely on spurious features $\unicode{x2013}$ patterns which are correlated with the target on the training data but not inherently relevant to the learning problem, such as the image backgrounds when classifying…

Machine Learning · Computer Science 2022-10-21 Pavel Izmailov , Polina Kirichenko , Nate Gruver , Andrew Gordon Wilson

We extend decision tree and random forest algorithms to product space manifolds: Cartesian products of Euclidean, hyperspherical, and hyperbolic manifolds. Such spaces have extremely expressive geometries capable of representing many…

Machine Learning · Computer Science 2025-05-08 Philippe Chlenski , Quentin Chu , Itsik Pe'er

We prove that kernel density estimation on symmetric spaces of non-compact type, whose L2-risk was bounded above in previous work (Asta,2021), in fact achieves a minimax rate of convergence. With this result, the story for kernel density…

Statistics Theory · Mathematics 2024-03-18 Dena Marie Asta

Despite their many appealing properties, kernel methods are heavily affected by the curse of dimensionality. For instance, in the case of inner product kernels in $\mathbb{R}^d$, the Reproducing Kernel Hilbert Space (RKHS) norm is often…

Machine Learning · Computer Science 2021-11-09 Michael Celentano , Theodor Misiakiewicz , Andrea Montanari

This paper proposes a framework dedicated to the construction of what we call discrete elastic inner product allowing one to embed sets of non-uniformly sampled multivariate time series or sequences of varying lengths into inner product…

Machine Learning · Computer Science 2012-06-28 Pierre-François Marteau , Nicolas Bonnel , Gilbas Ménier

We introduce random-kernel networks, a multilayer extension of random feature models where depth is created by deterministic kernel composition and randomness enters only in the outermost layer. We prove that deeper constructions can…

Machine Learning · Computer Science 2025-09-03 James Tian

In this paper we present a mathematical framework on linking of embeddings of compact topological spaces into Euclidean spaces and separability of linked embeddings under a specific class of dimension reduction maps. As applications of the…

General Topology · Mathematics 2025-11-11 Xiao-Song Yang

Despite the increasing importance of stochastic processes on linear networks and graphs, current literature on multivariate (vector-valued) Gaussian random fields on metric graphs is elusive. This paper challenges several aspects related to…

Statistics Theory · Mathematics 2025-01-20 Tobia Filosi , Emilio Porcu , Xavier Emery , Claudio Agostinelli , Alfredo Alegrìa

We show that kernel-based quadrature rules for computing integrals can be seen as a special case of random feature expansions for positive definite kernels, for a particular decomposition that always exists for such kernels. We provide a…

Machine Learning · Computer Science 2015-11-10 Francis Bach

The use of distributions and high-level features from deep architecture has become commonplace in modern computer vision. Both of these methodologies have separately achieved a great deal of success in many computer vision tasks. However,…

Machine Learning · Statistics 2021-01-15 Junier B. Oliva , Danica J. Sutherland , Barnabás Póczos , Jeff Schneider

Devoted to multi-task learning and structured output learning, operator-valued kernels provide a flexible tool to build vector-valued functions in the context of Reproducing Kernel Hilbert Spaces. To scale up these methods, we extend the…

Machine Learning · Computer Science 2018-05-25 Romain Brault , Florence d'Alché-Buc , Markus Heinonen

In the past decade, matrix factorization has been extensively researched and has become one of the most popular techniques for personalized recommendations. Nevertheless, the dot product adopted in matrix factorization based recommender…

Information Retrieval · Computer Science 2018-06-05 Shuai Zhang , Lina Yao , Yi Tay , Xiwei Xu , Xiang Zhang , Liming Zhu

Symmetric Positive Definite (SPD) matrices have become popular to encode image information. Accounting for the geometry of the Riemannian manifold of SPD matrices has proven key to the success of many algorithms. However, most existing…

Computer Vision and Pattern Recognition · Computer Science 2014-12-16 Sadeep Jayasumana , Richard Hartley , Mathieu Salzmann , Hongdong Li , Mehrtash Harandi

For supervised and unsupervised learning, positive definite kernels allow to use large and potentially infinite dimensional feature spaces with a computational cost that only depends on the number of observations. This is usually done…

Machine Learning · Computer Science 2008-09-10 Francis Bach

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