English
Related papers

Related papers: Average Case tractability of multivariate approxim…

200 papers

Despite the ubiquity of the Gaussian process regression model, few theoretical results are available that account for the fact that parameters of the covariance kernel typically need to be estimated from the dataset. This article provides…

Statistics Theory · Mathematics 2020-05-12 Toni Karvonen , George Wynne , Filip Tronarp , Chris J. Oates , Simo Särkkä

It is well-known that non-linear approximation has an advantage over linear schemes in the sense that it provides comparable approximation rates to those of the linear schemes, but to a larger class of approximands. This was established for…

Classical Analysis and ODEs · Mathematics 2010-04-28 Thomas Hangelbroek , Amos Ron

We consider an \eps-approximation by n-term partial sums of the Karhunen-Lo\`eve expansion to d-parametric random fields of tensor product-type in the average case setting. We investigate the behavior, as d tends to infinity, of the…

Probability · Mathematics 2012-08-15 N. Serdyukova

Gaussian processes are powerful, yet analytically tractable models for supervised learning. A Gaussian process is characterized by a mean function and a covariance function (kernel), which are determined by a model selection criterion. The…

Machine Learning · Statistics 2016-10-05 Benjamin Fischer , Nico Gorbach , Stefan Bauer , Yatao Bian , Joachim M. Buhmann

We study integration and $L^2$-approximation in the worst-case setting for deterministic linear algorithms based on function evaluations. The underlying function space is a reproducing kernel Hilbert space with a Gaussian kernel of tensor…

Numerical Analysis · Mathematics 2025-12-08 Michael Gnewuch , Klaus Ritter , Robin Rüßmann

In the last 20 years a whole hierarchy of notions of tractability was proposed and analyzed by several authors. These notions are used to classify the computational hardness of continuous numerical problems $S=(S_d)_{d\in\mathbb{N}}$ in…

Numerical Analysis · Mathematics 2014-11-14 Paweł Siedlecki , Markus Weimar

We consider the problem of performing linear regression over a stream of $d$-dimensional examples, and show that any algorithm that uses a subquadratic amount of memory exhibits a slower rate of convergence than can be achieved without…

Machine Learning · Computer Science 2020-10-13 Vatsal Sharan , Aaron Sidford , Gregory Valiant

This paper introduces a general method to approximate the convolution of an arbitrary program with a Gaussian kernel. This process has the effect of smoothing out a program. Our compiler framework models intermediate values in the program…

Graphics · Computer Science 2017-06-06 Yuting Yang , Connelly Barnes

Error entropy is a important nonlinear similarity measure, and it has received increasing attention in many practical applications. The default kernel function of error entropy criterion is Gaussian kernel function, however, which is not…

Signal Processing · Electrical Eng. & Systems 2023-09-06 Jiacheng He , Gang Wang , Bei Peng , Zhenyu Feng , Kun Zhang

Similarity learning has received a large amount of interest and is an important tool for many scientific and industrial applications. In this framework, we wish to infer the distance (similarity) between points with respect to an arbitrary…

Machine Learning · Statistics 2016-11-30 Michael Rabadi

Mixtures of Linear Regressions (MLR) is an important mixture model with many applications. In this model, each observation is generated from one of the several unknown linear regression components, where the identity of the generated…

Machine Learning · Computer Science 2020-03-31 Yuanzhi Li , Yingyu Liang

A large literature specifies conditions under which the information complexity for a sequence of numerical problems defined for dimensions $1, 2, \ldots$ grows at a moderate rate, i.e., the sequence of problems is tractable. Here, we focus…

Numerical Analysis · Mathematics 2024-04-24 Onyekachi Emenike , Fred J. Hickernell , Peter Kritzer

We approximate $d$-variate periodic functions in weighted Korobov spaces with general weight parameters using $n$ function values at lattice points. We do not limit $n$ to be a prime number, as in currently available literature, but allow…

Numerical Analysis · Mathematics 2022-09-05 Frances Y. Kuo , Weiwen Mo , Dirk Nuyens

Inference in popular nonparametric Bayesian models typically relies on sampling or other approximations. This paper presents a general methodology for constructing novel tractable nonparametric Bayesian methods by applying the kernel trick…

Machine Learning · Statistics 2011-08-15 Ferenc Huszár , Simon Lacoste-Julien

Kernel expansions are a topic of considerable interest in machine learning, also because of their relation to the so-called feature maps introduced in machine learning. Properties of the associated basis functions and weights (corresponding…

Machine Learning · Computer Science 2024-10-03 Mauro Bisiacco , Gianluigi Pillonetto

Gaussian processes regression models are an appealing machine learning method as they learn expressive non-linear models from exemplar data with minimal parameter tuning and estimate both the mean and covariance of unseen points. However,…

Machine Learning · Computer Science 2020-08-25 Vladimir Joukov , Dana Kulić

In this paper, we study error bounds for {\em Bayesian quadrature} (BQ), with an emphasis on noisy settings, randomized algorithms, and average-case performance measures. We seek to approximate the integral of functions in a {\em…

Machine Learning · Statistics 2023-02-13 Xu Cai , Chi Thanh Lam , Jonathan Scarlett

We study the problem of learning general (i.e., not necessarily homogeneous) halfspaces with Random Classification Noise under the Gaussian distribution. We establish nearly-matching algorithmic and Statistical Query (SQ) lower bound…

Machine Learning · Computer Science 2023-07-18 Ilias Diakonikolas , Jelena Diakonikolas , Daniel M. Kane , Puqian Wang , Nikos Zarifis

Gaussian Process (GP) models are often used as mathematical approximations of computationally expensive experiments. Provided that its kernel is suitably chosen and that enough data is available to obtain a reasonable fit of the simulator,…

Machine Learning · Statistics 2011-03-22 Nicolas Durrande , David Ginsbourger , Olivier Roustant

When estimating causal effects from observational studies, researchers often need to adjust for many covariates to deconfound the non-causal relationship between exposure and outcome, among which many covariates are discrete. The behavior…

Statistics Theory · Mathematics 2024-05-07 Zhenghao Zeng , Sivaraman Balakrishnan , Yanjun Han , Edward H. Kennedy