English
Related papers

Related papers: Exponential tractability of $L_2$-approximation wi…

200 papers

We consider the problem of evaluating representations of data for use in solving a downstream task. We propose to measure the quality of a representation by the complexity of learning a predictor on top of the representation that achieves…

Machine Learning · Computer Science 2021-02-08 William F. Whitney , Min Jae Song , David Brandfonbrener , Jaan Altosaar , Kyunghyun Cho

Policy evaluation with linear function approximation is an important problem in reinforcement learning. When facing high-dimensional feature spaces, such a problem becomes extremely hard considering the computation efficiency and quality of…

Machine Learning · Computer Science 2018-05-28 Haifang Li , Yingce Xia , Wensheng Zhang

Consider the model where we can access a parity function through random uniform labeled examples in the presence of random classification noise. In this paper, we show that approximating the number of relevant variables in the parity…

Machine Learning · Computer Science 2024-07-17 Nader H. Bshouty , George Haddad

Model complexity is an important factor to consider when selecting among graphical models. When all variables are observed, the complexity of a model can be measured by its standard dimension, i.e. the number of independent parameters. When…

Machine Learning · Computer Science 2013-01-07 Tomas Kocka , Nevin Lianwen Zhang

Eluder dimension and information gain are two widely used methods of complexity measures in bandit and reinforcement learning. Eluder dimension was originally proposed as a general complexity measure of function classes, but the common…

Machine Learning · Computer Science 2021-07-07 Kaixuan Huang , Sham M. Kakade , Jason D. Lee , Qi Lei

We consider the problem of approximating a function in general nonlinear subsets of $L^2$ when only a weighted Monte Carlo estimate of the $L^2$-norm can be computed. Of particular interest in this setting is the concept of sample…

Numerical Analysis · Mathematics 2021-08-12 Philipp Trunschke

Can we effectively learn a nonlinear representation in time comparable to linear learning? We describe a new algorithm that explicitly and adaptively expands higher-order interaction features over base linear representations. The algorithm…

Machine Learning · Computer Science 2014-10-03 Alekh Agarwal , Alina Beygelzimer , Daniel Hsu , John Langford , Matus Telgarsky

This is an expository paper on approximating functions from general Hilbert or Banach spaces in the worst case, average case and randomized settings with error measured in the $L_p$ sense. We define the power function as the ratio between…

Numerical Analysis · Mathematics 2011-06-08 Erich Novak , Henryk Woźniakowski

Dimensional correspondences have a long history in critical phenomena. Here, we review the effective dimension approach, which relates the scaling exponents of a critical system in $d$ spatial dimensions with power-law decaying interactions…

Statistical Mechanics · Physics 2024-12-17 Andrea Solfanelli , Nicolò Defenu

A number of machine learning algorithms are using a metric, or a distance, in order to compare individuals. The Euclidean distance is usually employed, but it may be more efficient to learn a parametric distance such as Mahalanobis metric.…

Machine Learning · Computer Science 2016-12-16 Hoel Le Capitaine

We study approximations of compact linear multivariate operators defined over Hilbert spaces. We provide necessary and sufficient conditions on various notions of tractability. These conditions are mainly given in terms of sums of certain…

Numerical Analysis · Mathematics 2018-07-10 Peter Kritzer , Henryk Wozniakowski

Recent advances in quasi-Monte Carlo integration demonstrate that the median of linearly scrambled digital net estimators achieves near-optimal convergence rates for high-dimensional integrals without requiring a priori knowledge of the…

Computation · Statistics 2026-02-03 Zexin Pan

Algorithms for learning decision trees often include heuristic local-search operations such as (1) adjusting the threshold of a cut or (2) also exchanging the feature of that cut. We study minimizing the number of classification errors by…

Machine Learning · Computer Science 2025-10-15 Juha Harviainen , Frank Sommer , Manuel Sorge

Estimation of a regression function from independent and identically distributed random variables is considered. The $L_2$ error with integration with respect to the design measure is used as an error criterion. Over-parametrized deep…

Statistics Theory · Mathematics 2022-10-05 Michael Kohler , Adam Krzyzak

Optimization problems are ubiquitous in our societies and are present in almost every segment of the economy. Most of these optimization problems are NP-hard and computationally demanding, often requiring approximate solutions for…

Optimization and Control · Mathematics 2021-06-23 James Kotary , Ferdinando Fioretto , Pascal Van Hentenryck

We address the problem of estimating a high-dimensional matrix from linear measurements, with a focus on designing optimal rank-adaptive algorithms. These algorithms infer the matrix by estimating its singular values and the corresponding…

Information Theory · Computer Science 2026-05-12 Frédéric Zheng , Yassir Jedra , Alexandre Proutiere

We consider a class of linear eigenvalue problems depending on a small parameter epsilon in which the series expansion for the eigenvalue in powers of epsilon is divergent. We develop a new technique to determine the precise nature of this…

Classical Analysis and ODEs · Mathematics 2026-02-04 Stephen Jonathan Chapman

The unadjusted Langevin algorithm is commonly used to sample probability distributions in extremely high-dimensional settings. However, existing analyses of the algorithm for strongly log-concave distributions suggest that, as the dimension…

Machine Learning · Statistics 2025-09-05 Yifan Chen , Xiaoou Cheng , Jonathan Niles-Weed , Jonathan Weare

In this paper, we study multivariate approximation defined over weighted anisotropic Sobolev spaces which depend on two sequences ${\bf a}=\{a_j\}_{j\geq1}$ and ${\bf b}=\{b_j\}_{j\geq1}$ of positive numbers. We obtain strong equivalences…

Numerical Analysis · Mathematics 2019-07-02 JiDong Hao , Heping Wang

Empirical process theory for i.i.d. observations has emerged as a ubiquitous tool for understanding the generalization properties of various statistical problems. However, in many applications where the data exhibit temporal dependencies…

Statistics Theory · Mathematics 2024-01-18 Nabarun Deb , Debarghya Mukherjee
‹ Prev 1 4 5 6 7 8 10 Next ›