English
Related papers

Related papers: Precise Asymptotic Generalization for Multiclass C…

200 papers

Rerandomization is an effective treatment allocation procedure to control for baseline covariate imbalance. For estimating the average treatment effect, rerandomization has been previously shown to improve the precision of the unadjusted…

Methodology · Statistics 2026-05-18 Bingkai Wang , Fan Li

The Gaussian graphical model, a popular paradigm for studying relationship among variables in a wide range of applications, has attracted great attention in recent years. This paper considers a fundamental question: When is it possible to…

Statistics Theory · Mathematics 2015-06-04 Zhao Ren , Tingni Sun , Cun-Hui Zhang , Harrison H. Zhou

A recent article on generalised linear mixed model asymptotics, Jiang et al. (2022), derived the rates of convergence for the asymptotic variances of maximum likelihood estimators. If $m$ denotes the number of groups and $n$ is the average…

Statistics Theory · Mathematics 2023-04-03 Luca Maestrini , Aishwarya Bhaskaran , Matt P. Wand

Reviewing the semiclassical theory for the parametric level density fluctuations, we show that for large parametric changes the density correlation function, after rescaling, becomes universal and coincides with the leading asymptotic term…

In modern scientific applications, large volumes of covariate data are readily available, while outcome labels are costly, sparse, and often subject to distribution shift. This asymmetry has spurred interest in semi-supervised (SS)…

Statistics Theory · Mathematics 2026-05-12 Lorenzo Testa , Qi Xu , Jing Lei , Kathryn Roeder

Meta-learning has arisen as a successful method for improving training performance by training over many similar tasks, especially with deep neural networks (DNNs). However, the theoretical understanding of when and why overparameterized…

Machine Learning · Computer Science 2023-04-11 Peizhong Ju , Yingbin Liang , Ness B. Shroff

Within the machine learning community, the widely-used uniform convergence framework has been used to answer the question of how complex, over-parameterized models can generalize well to new data. This approach bounds the test error of the…

Machine Learning · Statistics 2021-03-05 Ryan Theisen , Jason M. Klusowski , Michael W. Mahoney

Graph-based methods play an important role in unsupervised and semi-supervised learning tasks by taking into account the underlying geometry of the data set. In this paper, we consider a statistical setting for semi-supervised learning and…

Machine Learning · Computer Science 2015-02-17 Aamir Anis , Aly El Gamal , A. Salman Avestimehr , Antonio Ortega

Downsampling or under-sampling is a technique that is utilized in the context of large and highly imbalanced classification models. We study optimal downsampling for imbalanced classification using generalized linear models (GLMs). We…

Machine Learning · Statistics 2025-05-20 Yan Chen , Jose Blanchet , Krzysztof Dembczynski , Laura Fee Nern , Aaron Flores

At the heart of machine learning lies the question of generalizability of learned rules over previously unseen data. While over-parameterized models based on neural networks are now ubiquitous in machine learning applications, our…

Machine Learning · Computer Science 2020-05-04 Melikasadat Emami , Mojtaba Sahraee-Ardakan , Parthe Pandit , Sundeep Rangan , Alyson K. Fletcher

This tutorial serves as an introduction to recently developed non-asymptotic methods in the theory of -- mainly linear -- system identification. We emphasize tools we deem particularly useful for a range of problems in this domain, such as…

Systems and Control · Electrical Eng. & Systems 2024-06-18 Ingvar Ziemann , Anastasios Tsiamis , Bruce Lee , Yassir Jedra , Nikolai Matni , George J. Pappas

The rapid recent progress in machine learning (ML) has raised a number of scientific questions that challenge the longstanding dogma of the field. One of the most important riddles is the good empirical generalization of overparameterized…

Machine Learning · Statistics 2021-09-07 Yehuda Dar , Vidya Muthukumar , Richard G. Baraniuk

This paper establishes a precise high-dimensional asymptotic theory for boosting on separable data, taking statistical and computational perspectives. We consider a high-dimensional setting where the number of features (weak learners) $p$…

Statistics Theory · Mathematics 2022-11-21 Tengyuan Liang , Pragya Sur

Reduced-rank regression is a dimensionality reduction method with many applications. The asymptotic theory for reduced rank estimators of parameter matrices in multivariate linear models has been studied extensively. In contrast, few…

Statistics Theory · Mathematics 2017-10-13 Efstathia Bura , Sabrina Duarte , Liliana Forzani , Ezequiel Smucler , Mariela Sued

We consider high-dimensional multiclass classification by sparse multinomial logistic regression. Unlike binary classification, in the multiclass setup one can think about an entire spectrum of possible notions of sparsity associated with…

Statistics Theory · Mathematics 2023-01-18 Tomer Levy , Felix Abramovich

Benign overfitting, the phenomenon where interpolating models generalize well in the presence of noisy data, was first observed in neural network models trained with gradient descent. To better understand this empirical observation, we…

Machine Learning · Computer Science 2025-07-04 Spencer Frei , Niladri S. Chatterji , Peter L. Bartlett

We study the use of linear regression for multiclass classification in the over-parametrized regime where some of the training data is mislabeled. In such scenarios it is necessary to add an explicit regularization term, $\lambda f(w)$, for…

Machine Learning · Computer Science 2024-10-14 Reza Ghane , Danil Akhtiamov , Babak Hassibi

We examine the necessity of interpolation in overparameterized models, that is, when achieving optimal predictive risk in machine learning problems requires (nearly) interpolating the training data. In particular, we consider simple…

Machine Learning · Statistics 2022-06-17 Chen Cheng , John Duchi , Rohith Kuditipudi

The objective of the paper is to study accuracy of multi-class classification in high-dimensional setting, where the number of classes is also large ("large $L$, large $p$, small $n$" model). While this problem arises in many practical…

Statistics Theory · Mathematics 2019-07-18 Felix Abramovich , Marianna Pensky

This paper considers the classification of linear subspaces with mismatched classifiers. In particular, we assume a model where one observes signals in the presence of isotropic Gaussian noise and the distribution of the signals conditioned…

Information Theory · Computer Science 2016-05-04 Jure Sokolic , Francesco Renna , Robert Calderbank , Miguel R. D. Rodrigues