English
Related papers

Related papers: Optimal Dimension-Free Sampling for Regularized Cl…

200 papers

We consider the problem of classification of functional data into two groups by linear classifiers based on one-dimensional projections of functions. We reformulate the task to find the best classifier as an optimization problem and solve…

Methodology · Statistics 2017-08-29 David Kraus , Marco Stefanucci

Consider the class of optimal partition problems with long range interactions \[ \inf \left\{ \sum_{i=1}^k \lambda_1(\omega_i):\ (\omega_1,\ldots, \omega_k) \in \mathcal{P}_r(\Omega) \right\}, \] where $\lambda_1(\cdot)$ denotes the first…

Analysis of PDEs · Mathematics 2021-06-08 Nicola Soave , Hugo Tavares , Alessandro Zilio

We investigate the properties of minimizers of one-dimensional variational problems when the Lagrangian has no higher smoothness than continuity. An elementary approximation result is proved, but it is shown that this cannot be in general…

Classical Analysis and ODEs · Mathematics 2017-04-12 Richard Gratwick

In this paper, we study private optimization problems for non-smooth convex functions $F(x)=\mathbb{E}_i f_i(x)$ on $\mathbb{R}^d$. We show that modifying the exponential mechanism by adding an $\ell_2^2$ regularizer to $F(x)$ and sampling…

Data Structures and Algorithms · Computer Science 2022-07-29 Sivakanth Gopi , Yin Tat Lee , Daogao Liu

In the development of first-order methods for smooth (resp., composite) convex optimization problems, where smooth functions with Lipschitz continuous gradients are minimized, the gradient (resp., gradient mapping) norm becomes a…

Optimization and Control · Mathematics 2020-10-06 Masaru Ito , Mituhiro Fukuda

We consider the problem of minimizing a continuous function f over a compact set K. We analyze a hierarchy of upper bounds proposed by Lasserre in [SIAM J. Optim. 21(3) (2011), pp. 864--885], obtained by searching for an optimal probability…

Optimization and Control · Mathematics 2015-09-09 Etienne de Klerk , Monique Laurent , Zhao Sun

This paper introduces a new parameterization of deep neural networks (both fully-connected and convolutional) with guaranteed $\ell^2$ Lipschitz bounds, i.e. limited sensitivity to input perturbations. The Lipschitz guarantees are…

Machine Learning · Computer Science 2023-06-07 Ruigang Wang , Ian R. Manchester

We propose a dimension reduction technique for Bayesian inverse problems with nonlinear forward operators, non-Gaussian priors, and non-Gaussian observation noise. The likelihood function is approximated by a ridge function, i.e., a map…

Probability · Mathematics 2022-01-31 Olivier Zahm , Tiangang Cui , Kody Law , Alessio Spantini , Youssef Marzouk

This paper proves an abstract theorem addressing in a unified manner two important problems in function approximation: avoiding curse of dimensionality and estimating the degree of approximation for out-of-sample extension in manifold…

Machine Learning · Computer Science 2019-11-05 Hrushikesh N. Mhaskar

We initiate a program of average smoothness analysis for efficiently learning real-valued functions on metric spaces. Rather than using the Lipschitz constant as the regularizer, we define a local slope at each point and gauge the function…

Statistics Theory · Mathematics 2020-11-10 Yair Ashlagi , Lee-Ad Gottlieb , Aryeh Kontorovich

A new lower bound on the average reconstruction error variance of multidimensional sampling and reconstruction is presented. It applies to sampling on arbitrary lattices in arbitrary dimensions, assuming a stochastic process with constant,…

Information Theory · Computer Science 2018-06-19 Erik Agrell , Balázs Csébfalvi

We develop new solvability methods for divergence form second order, real and complex, elliptic systems above Lipschitz graphs, with $L_2$ boundary data. The coefficients $A$ may depend on all variables, but are assumed to be close to…

Analysis of PDEs · Mathematics 2010-09-16 Pascal Auscher , Andreas Axelsson

We study the sample complexity of differentially private optimization of quasi-concave functions. For a fixed input domain $\mathcal{X}$, Cohen et al. (STOC 2023) proved that any generic private optimizer for low sensitive quasi-concave…

Cryptography and Security · Computer Science 2025-04-29 Kobbi Nissim , Eliad Tsfadia , Chao Yan

We study monotonicity testing of functions $f \colon \{0,1\}^d \to \{0,1\}$ using sample-based algorithms, which are only allowed to observe the value of $f$ on points drawn independently from the uniform distribution. A classic result by…

Data Structures and Algorithms · Computer Science 2024-08-21 Hadley Black

Covering numbers of (deep) ReLU networks have been used to characterize approximation-theoretic performance, to upper-bound prediction error in nonparametric regression, and to quantify classification capacity. These results rely on…

Machine Learning · Statistics 2026-03-04 Weigutian Ou , Helmut Bölcskei

In this paper, we propose a coupled tensor norm regularization that could enable the model output feature and the data input to lie in a low-dimensional manifold, which helps us to reduce overfitting. We show this regularization term is…

Optimization and Control · Mathematics 2023-02-24 Ying Gao , Yunfei Qu , Chunfeng Cui , Deren Han

$D$-optimal designs originate in statistics literature as an approach for optimal experimental designs. In numerical analysis points and weights resulting from maximal determinants turned out to be useful for quadrature and interpolation.…

Numerical Analysis · Mathematics 2024-12-04 Felix Bartel , Lutz Kämmerer , Kateryna Pozharska , Martin Schäfer , Tino Ullrich

We derive a tight generalization bound for quantum machine learning that is applicable to a wide range of supervised tasks, data, and models. Our bound is both efficiently computable and free of big-O notation. Furthermore, we point out…

Quantum Physics · Physics 2025-10-29 Xin Wang , Rebing Wu

Consider a regression problem where the learner is given a large collection of $d$-dimensional data points, but can only query a small subset of the real-valued labels. How many queries are needed to obtain a $1+\epsilon$ relative error…

Machine Learning · Computer Science 2021-06-29 Xue Chen , Michał Dereziński

This paper studies approximation by shallow ReLU$^s$ networks, $\sigma_s(t)=\max\{0,t\}^s$, together with their generalization behavior under $\ell_1$ path-norm control. For the $L^p$-type integral spaces…

Machine Learning · Statistics 2026-05-27 Weizhao Li , Fanghui Liu , Lei Shi
‹ Prev 1 8 9 10 Next ›