Kernel methods are a highly effective and widely used collection of modern machine learning algorithms. A fundamental limitation of virtually all such methods are computations involving the kernel matrix that naively scale quadratically (e.g., constructing the kernel matrix and matrix-vector multiplication) or cubically (solving linear systems) with the size of the data set $N.$ We propose the Fast Kernel Transform (FKT), a general algorithm to compute matrix-vector multiplications (MVMs) for datasets in moderate dimensions with quasilinear complexity. Typically, analytically grounded fast multiplication methods require specialized development for specific kernels. In contrast, our scheme is based on auto-differentiation and automated symbolic computations that leverage the analytical structure of the underlying kernel. This allows the FKT to be easily applied to a broad class of kernels, including Gaussian, Matern, and Rational Quadratic covariance functions and physically motivated Green's functions, including those of the Laplace and Helmholtz equations. Furthermore, the FKT maintains a high, quantifiable, and controllable level of accuracy -- properties that many acceleration methods lack. We illustrate the efficacy and versatility of the FKT by providing timing and accuracy benchmarks and by applying it to scale the stochastic neighborhood embedding (t-SNE) and Gaussian processes to large real-world data sets.
Fast Gaussian process inference by exact Matérn kernel decomposition
Guangdong Provincial/Zhuhai Key Laboratory of Interdisciplinary Research and Application for Data Science, Beijing Normal-Hong Kong Baptist University(广东/珠海交叉学科与数据科学应用重点实验室,北京师范大学-香港 Baptist大学);EDF Lab, FiME (Laboratoire de Finance des Marchés de l’Énergie)(EDF实验室,FiME(能源市场金融实验室))
Faster Kernel Matrix Algebra via Density Estimation
Toyota Technological Institute at Chicago(芝加哥丰田技术研究所);Massachusetts Institute of Technology(麻省理工学院);University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校);Microsoft Research(微软研究院)
In this work we introduce KERNELIZED TRANSFORMER, a generic, scalable, data driven framework for learning the kernel function in Transformers. Our framework approximates the Transformer kernel as a dot product between spectral feature maps and learns the kernel by learning the spectral distribution. This not only helps in learning a generic kernel end-to-end, but also reduces the time and space complexity of Transformers from quadratic to linear. We show that KERNELIZED TRANSFORMERS achieve performance comparable to existing efficient Transformer architectures, both in terms of accuracy as wel…
We demonstrate a simple connection between dictionary methods for time series classification, which involve extracting and counting symbolic patterns in time series, and methods based on transforming input time series using convolutional kernels, namely ROCKET and its variants. We show that by adjusting a single hyperparameter it is possible to move by degrees between models resembling dictionary methods and models resembling ROCKET. We present HYDRA, a simple, fast, and accurate dictionary method for time series classification using competing convolutional kernels, combining key aspects of bo…
Fast Approximation and Estimation Bounds of Kernel Quadrature for Infinitely Wide Models
RIKEN AIP(日本理化学研究所革新智能综合研究中心)
无限宽模型是特征图的加权积分$\int φ(x,v) d μ(v)$。该模型擅长处理无限数量的特征,因此已被用于深度学习的理论研究。核求积是一种基于核的数值积分方案,用于快速逼近期望值$\int f(x) d p(x)$。在这项研究中,关于重量$μ$作为一个有符号(或复杂/向量值)分布的参数,我们开发的一般核求积(GKQ)的参数分布。所提出的方法可以实现一个快速的近似速度$O(e^{-p})$与参数数$p$,这是比传统的巴伦的速度,和一个快速的估计速度$\widetilde{O}(1/n)$与样本量$n$。因此,我们得到了一个新的基于范数的复杂性度量的无限宽模型。由于GKQ隐式地进行经验风险最小化,因此我们可以理解复杂性度量也反映了梯度学习设置中的泛化性能。
Graduate School of Information Science and Technology, The University of Tokyo(东京大学信息科学与技术研究生院)
核方法是分析结构化数据(如序列、树和图)的一种潜在方法,然而,无序树尚未得到广泛研究。Kimura et al.(2011)提出了一种基于子路径的无序树的核函数,子路径是树的垂直子结构,负责其中的层次信息。他们的内核在精度和速度方面表现出实际上很好的性能;然而,线性时间计算在理论上不能保证,不像Vishwanathan和Smola(2003)提出的其他无序树内核。在本文中,我们提出了一个理论上保证线性时间内核计算算法,实际上是快速的,我们提出了一个有效的预测算法,其运行时间只取决于输入树的大小。实验结果表明,本文提出的算法在实际应用中是非常有效的.
The Clinical Hospital of Chengdu Brain Science Institute(成都脑科学研究院临床医院);University of Electronic Science and Technology of China(电子科技大学);Cuban Center for Neuroscience(古巴神经科学中心)
Kernel smooth is the most fundamental technique for data density and regression estimation. However, time-consuming is the biggest obstacle for the application that the direct evaluation of kernel smooth for $N$ samples needs ${O}\left( {{N}^{2}} \right)$ operations. People have developed fast smooth algorithms using the idea of binning with FFT. Unfortunately, the accuracy is not controllable, and the implementation for multivariable and its bandwidth selection for the fast method is not available. Hence, we introduce a new MATLAB toolbox for fast multivariate kernel regression with the idea …
Fast and Extensible Online Multivariate Kernel Density Estimation
INESC ID Lisboa(里斯本高等工程学院信息与决策系统研究所);Instituto Superior Técnico, Universidade de Lisboa(里斯本大学高等技术学院);Instituto Universitário de Lisboa (ISCTE-IUL)(里斯本大学学院(ISCTE-IUL))
MindLab(思维实验室);Universidad Nacional de Colombia(哥伦比亚国立大学)
Kernel density estimation (KDE) is one of the most widely used nonparametric density estimation methods. The fact that it is a memory-based method, i.e., it uses the entire training data set for prediction, makes it unsuitable for most current big data applications. Several strategies, such as tree-based or hashing-based estimators, have been proposed to improve the efficiency of the kernel density estimation method. The novel density kernel density estimation method (DMKDE) uses density matrices, a quantum mechanical formalism, and random Fourier features, an explicit kernel approximation, to…
Inria(法国国家信息与自动化研究所);Ecole Normale Supérieure(巴黎高等师范学院);PSL Research University(巴黎文理研究大学)
We consider potentially non-convex optimization problems, for which optimal rates of approximation depend on the dimension of the parameter space and the smoothness of the function to be optimized. In this paper, we propose an algorithm that achieves close to optimal a priori computational guarantees, while also providing a posteriori certificates of optimality. Our general formulation builds on infinite-dimensional sums-of-squares and Fourier analysis, and is instantiated on the minimization of multivariate periodic functions.
Fast and Scalable Score-Based Kernel Calibration Tests
Gatsby Computational Neuroscience Unit(加布特计算神经科学单位);University College London(伦敦大学学院);Department of Information Technology(信息技术系);Uppsala University(乌普萨拉大学);Division of Statistics and Machine Learning(统计与机器学习 division);Linköping University(林雪平大学)
Learning in High-Dimensional Feature Spaces Using ANOVA-Based Fast Matrix-Vector Multiplication
TU Chemnitz(开姆尼茨工业大学);Department of Mathematics, Chair of Applied Functional Analysis(数学系应用泛函分析讲席);Department of Mathematics, Chair of Scientific Computing(数学系科学计算讲席)
Jiangxi Normal University(江西师范大学);Xi’an Jiaotong University(西安交通大学);University of Sydney(悉尼大学)
In the era of big data, it is desired to develop efficient machine learning algorithms to tackle massive data challenges such as storage bottleneck, algorithmic scalability, and interpretability. In this paper, we develop a novel efficient classification algorithm, called fast polynomial kernel classification (FPC), to conquer the scalability and storage challenges. Our main tools are a suitable selected feature mapping based on polynomial kernels and an alternating direction method of multipliers (ADMM) algorithm for a related non-smooth convex optimization problem. Fast learning rates as wel…