English
Related papers

Related papers: Dimension-Free Bounds for Generalized First-Order …

200 papers

Stochastic iterative algorithms, including stochastic gradient descent (SGD) and stochastic gradient Langevin dynamics (SGLD), are widely utilized for optimization and sampling in large-scale and high-dimensional problems in machine…

Machine Learning · Statistics 2025-01-22 Xiaoyu Wang , Mikolaj J. Kasprzak , Jeffrey Negrea , Solesne Bourguin , Jonathan H. Huggins

Many functions have approximately-known upper and/or lower bounds, potentially aiding the modeling of such functions. In this paper, we introduce Gaussian process models for functions where such bounds are (approximately) known. More…

Machine Learning · Computer Science 2022-10-20 Vu Nguyen , Marc Peter Deisenroth , Michael A. Osborne

Gaussian couplings of partial sum processes are derived for the high-dimensional regime $d=o(n^{1/3})$. The coupling is derived for sums of independent random vectors and subsequently extended to nonstationary time series. Our inequalities…

Probability · Mathematics 2022-03-08 Fabian Mies , Ansgar Steland

Many learning paradigms self-select training data in light of previously learned parameters. Examples include active learning, semi-supervised learning, bandits, or boosting. Rodemann et al. (2024) unify them under the framework of…

Machine Learning · Computer Science 2025-05-13 Julian Rodemann , James Bailie

We study Bayesian estimation of finite mixture models in a general setup where the number of components is unknown and allowed to grow with the sample size. An assumption on growing number of components is a natural one as the degree of…

Statistics Theory · Mathematics 2022-03-18 Ilsang Ohn , Lizhen Lin

In this paper, we establish novel data-dependent upper bounds on the generalization error through the lens of a "variable-size compressibility" framework that we introduce newly here. In this framework, the generalization error of an…

Machine Learning · Statistics 2024-06-12 Milad Sefidgaran , Abdellatif Zaidi

Randomized methods, such as the randomized SVD (singular value decomposition) and Nystr\"om approximation, are an effective way to compute low-rank approximations of large matrices. Motivated by applications to operator learning, Boull\'e…

Numerical Analysis · Mathematics 2026-02-09 Daniel Kressner , David Persson , André Uschmajew

We derive nearly sharp bounds for the bidirectional GAN (BiGAN) estimation error under the Dudley distance between the latent joint distribution and the data joint distribution with appropriately specified architecture of the neural…

Machine Learning · Computer Science 2021-10-26 Shiao Liu , Yunfei Yang , Jian Huang , Yuling Jiao , Yang Wang

When the nonconvex problem is complicated by stochasticity, the sample complexity of stochastic first-order methods may depend linearly on the problem dimension, which is undesirable for large-scale problems. In this work, we propose…

Optimization and Control · Mathematics 2024-10-01 Yue Xie , Jiawen Bi , Hongcheng Liu

In a recent paper, the authors proposed a new class of low-complexity iterative thresholding algorithms for reconstructing sparse signals from a small set of linear measurements \cite{DMM}. The new algorithms are broadly referred to as AMP,…

Information Theory · Computer Science 2009-11-24 David L. Donoho , Arian Maleki , Andrea Montanari

Established approaches to obtain generalization bounds in data-driven optimization and machine learning mostly build on solutions from empirical risk minimization (ERM), which depend crucially on the functional complexity of the hypothesis…

Optimization and Control · Mathematics 2022-10-14 Yibo Zeng , Henry Lam

We study the deterministic global optimization of trained Gaussian process posterior mean functions over hyperrectangular domains. Although the posterior mean function has a compact closed-form representation, its global optimization is…

Optimization and Control · Mathematics 2026-05-05 Wei-Ting Tang , Akshay Kudva , Calvin Tsay , Joel A. Paulson

A simple model to study subspace clustering is the high-dimensional $k$-Gaussian mixture model where the cluster means are sparse vectors. Here we provide an exact asymptotic characterization of the statistically optimal reconstruction…

Machine Learning · Statistics 2023-04-04 Luca Pesce , Bruno Loureiro , Florent Krzakala , Lenka Zdeborová

We provide non-asymptotic bounds for first and higher order inclusion probabilities of the rejective sampling model with various size parameters. Further we derive bounds in the semi-definite ordering for matrices that collect (conditional)…

Probability · Mathematics 2022-12-20 Simon Ruetz , Karin Schnass

First order optimization algorithms play a major role in large scale machine learning. A new class of methods, called adaptive algorithms, were recently introduced to adjust iteratively the learning rate for each coordinate. Despite great…

Machine Learning · Computer Science 2019-10-01 André Belotto da Silva , Maxime Gazeau

We describe a general technique that yields the first {\em Statistical Query lower bounds} for a range of fundamental high-dimensional learning problems involving Gaussian distributions. Our main results are for the problems of (1) learning…

Machine Learning · Computer Science 2017-05-18 Ilias Diakonikolas , Daniel M. Kane , Alistair Stewart

Given any deep fully connected neural network, initialized with random Gaussian parameters, we bound from above the quadratic Wasserstein distance between its output distribution and a suitable Gaussian process. Our explicit inequalities…

Machine Learning · Computer Science 2023-09-25 Andrea Basteri , Dario Trevisan

Large-margin classifiers are popular methods for classification. We derive the asymptotic expression for the generalization error of a family of large-margin classifiers in the limit of both sample size $n$ and dimension $p$ going to…

Machine Learning · Statistics 2020-12-02 Hanwen Huang , Qinglong Yang

In this paper, we focus on the data-driven discovery of a general second-order particle-based model that contains many state-of-the-art models for modeling the aggregation and collective behavior of interacting agents of similar size and…

Machine Learning · Statistics 2023-11-03 Jinchao Feng , Charles Kulick , Sui Tang

In this paper, we study non-asymptotic deviation bounds of the least squares estimator in Gaussian AR($n$) processes. By relying on martingale concentration inequalities and a tail-bound for $\chi^2$ distributed variables, we provide a…

Machine Learning · Statistics 2020-05-26 Rodrigo A. González , Cristian R. Rojas
‹ Prev 1 8 9 10 Next ›