English
Related papers

Related papers: Sampling discretization error of integral norms fo…

200 papers

Stochastic gradient descent samples uniformly the training set to build an unbiased gradient estimate with a limited number of samples. However, at a given step of the training process, some data are more helpful than others to continue…

Machine Learning · Computer Science 2023-03-30 Thibault Lahire

Group-invariant probability distributions appear in many data-generative models in machine learning, such as graphs, point clouds, and images. In practice, one often needs to estimate divergences between such distributions. In this work, we…

Machine Learning · Computer Science 2026-02-05 Behrooz Tahmasebi , Stefanie Jegelka

Randomized smoothing, a method to certify a classifier's decision on an input is invariant under adversarial noise, offers attractive advantages over other certification methods. It operates in a black-box and so certification is not…

Machine Learning · Computer Science 2020-06-09 Jamie Hayes

The randomized midpoint method, proposed by [SL19], has emerged as an optimal discretization procedure for simulating the continuous time Langevin diffusions. Focusing on the case of strong-convex and smooth potentials, in this paper, we…

Machine Learning · Statistics 2021-09-14 Ye He , Krishnakumar Balasubramanian , Murat A. Erdogdu

Self-training is a classical approach in semi-supervised learning which is successfully applied to a variety of machine learning problems. Self-training algorithm generates pseudo-labels for the unlabeled examples and progressively refines…

Machine Learning · Computer Science 2020-06-22 Samet Oymak , Talha Cihad Gulcu

The computational cost of training with softmax cross entropy loss grows linearly with the number of classes. For the settings where a large number of classes are involved, a common method to speed up training is to sample a subset of…

Machine Learning · Computer Science 2020-01-01 Ankit Singh Rawat , Jiecao Chen , Felix Yu , Ananda Theertha Suresh , Sanjiv Kumar

We study the problem of sampling from a target distribution in $\mathbb{R}^d$ whose potential is not smooth. Compared with the sampling problem with smooth potentials, this problem is much less well-understood due to the lack of smoothness.…

Computation · Statistics 2023-07-25 Jiaojiao Fan , Bo Yuan , Jiaming Liang , Yongxin Chen

Building upon recent advances in entropy-regularized optimal transport, and upon Fenchel duality between measures and continuous functions , we propose a generalization of the logistic loss that incorporates a metric or cost between…

Machine Learning · Statistics 2019-05-16 Arthur Mensch , Mathieu Blondel , Gabriel Peyré

We study the complexity of approximating integrals of smooth functions at absolute precision $\varepsilon > 0$ with confidence level $1 - \delta \in (0,1)$. The optimal error rate for multivariate functions from classical isotropic Sobolev…

Numerical Analysis · Mathematics 2018-09-27 Robert J. Kunsch , Daniel Rudolf

We calculate universal finite-size scaling functions for systems with an n-component order parameter and algebraically decaying interactions. Just as previously has been found for short-range interactions, this leads to a singular…

Statistical Mechanics · Physics 2009-10-31 Erik Luijten

We consider the problem of unconstrained minimization of a smooth objective function in $\R^n$ in a setting where only function evaluations are possible. While importance sampling is one of the most popular techniques used by machine…

Optimization and Control · Mathematics 2020-04-03 Adel Bibi , El Houcine Bergou , Ozan Sener , Bernard Ghanem , Peter Richtárik

This paper studies the unsupervised embedding learning problem, which requires an effective similarity measurement between samples in low-dimensional embedding space. Motivated by the positive concentrated and negative separated properties…

Computer Vision and Pattern Recognition · Computer Science 2019-04-09 Mang Ye , Xu Zhang , Pong C. Yuen , Shih-Fu Chang

We study the problem of estimating a distribution over a finite alphabet from an i.i.d. sample, with accuracy measured in relative entropy (Kullback-Leibler divergence). While optimal bounds on the expected risk are known, high-probability…

Statistics Theory · Mathematics 2026-02-27 Jaouad Mourtada

The problem of estimating the mean of random functions based on discretely sampled data arises naturally in functional data analysis. In this paper, we study optimal estimation of the mean function under both common and independent designs.…

Statistics Theory · Mathematics 2012-02-24 T. Tony Cai , Ming Yuan

We investigate the learning dynamics of classifiers in scenarios where classes are separable or classifiers are over-parameterized. In both cases, Empirical Risk Minimization (ERM) results in zero training error. However, there are many…

Machine Learning · Computer Science 2024-10-23 Julius Martinetz , Christoph Linse , Thomas Martinetz

We study a class of importance sampling methods for stochastic differential equations (SDEs). A small-noise analysis is performed, and the results suggest that a simple symmetrization procedure can significantly improve the performance of…

Numerical Analysis · Mathematics 2018-07-04 Andrew Leach , Kevin K. Lin , Matthias Morzfeld

Stochastic Approximation (SA) is a popular approach for solving fixed-point equations where the information is corrupted by noise. In this paper, we consider an SA involving a contraction mapping with respect to an arbitrary norm, and show…

Machine Learning · Computer Science 2021-07-01 Zaiwei Chen , Siva Theja Maguluri , Sanjay Shakkottai , Karthikeyan Shanmugam

Location estimation is a central problem in functional data analysis. In this paper, we investigate penalized spline estimators of location for discretely sampled functional data under a broad class of convex loss functions. Our framework…

Methodology · Statistics 2025-08-19 Ioannis Kalogridis

Diffusion models have had a profound impact on many application areas, including those where data are intrinsically infinite-dimensional, such as images or time series. The standard approach is first to discretize and then to apply…

Machine Learning · Statistics 2025-06-09 Jakiw Pidstrigach , Youssef Marzouk , Sebastian Reich , Sven Wang

We prove the curse of dimensionality in the worst case setting for multivariate numerical integration for various classes of smooth functions. We prove the results when the domains are isotropic convex bodies with small diameter satisfying…

Numerical Analysis · Mathematics 2019-08-15 Aicke Hinrichs , Joscha Prochno , Mario Ullrich