A model of double descent for high-dimensional binary linear classification
We consider a model for logistic regression where only a subset of features of size is used
for training a linear classifier over training samples. The classifier is obtained by running …
for training a linear classifier over training samples. The classifier is obtained by running …
A precise high-dimensional asymptotic theory for boosting and minimum--norm interpolated classifiers
A precise high-dimensional asymptotic theory for boosting and minimum-l1-norm
interpolated classifiers Page 1 The Annals of Statistics 2022, Vol. 50, No. 3, 1669–1695 …
interpolated classifiers Page 1 The Annals of Statistics 2022, Vol. 50, No. 3, 1669–1695 …
Precise statistical analysis of classification accuracies for adversarial training
A Javanmard, M Soltanolkotabi - The Annals of Statistics, 2022 - projecteuclid.org
Precise statistical analysis of classification accuracies for adversarial training Page 1 The
Annals of Statistics 2022, Vol. 50, No. 4, 2127–2156 https://doi.org/10.1214/22-AOS2180 © …
Annals of Statistics 2022, Vol. 50, No. 4, 2127–2156 https://doi.org/10.1214/22-AOS2180 © …
The curse of overparametrization in adversarial training: Precise analysis of robust generalization for random features regression
H Hassani, A Javanmard - The Annals of Statistics, 2024 - projecteuclid.org
The curse of overparametrization in adversarial training: Precise analysis of robust
generalization for random features regressi Page 1 The Annals of Statistics 2024, Vol. 52, No. 2 …
generalization for random features regressi Page 1 The Annals of Statistics 2024, Vol. 52, No. 2 …
Theoretical insights into multiclass classification: A high-dimensional asymptotic view
C Thrampoulidis, S Oymak… - Advances in Neural …, 2020 - proceedings.neurips.cc
Contemporary machine learning applications often involve classification tasks with many
classes. Despite their extensive use, a precise understanding of the statistical properties and …
classes. Despite their extensive use, a precise understanding of the statistical properties and …
Universality of regularized regression estimators in high dimensions
Universality of regularized regression estimators in high dimensions Page 1 The Annals of
Statistics 2023, Vol. 51, No. 4, 1799–1823 https://doi.org/10.1214/23-AOS2309 © Institute of …
Statistics 2023, Vol. 51, No. 4, 1799–1823 https://doi.org/10.1214/23-AOS2309 © Institute of …
Survey on algorithms of people counting in dense crowd and crowd density estimation
G Yang, D Zhu - Multimedia Tools and Applications, 2023 - Springer
The number of people and the estimation of the population density are one of the important
information concerned by intelligent monitoring. This article reviews, summarizes, and …
information concerned by intelligent monitoring. This article reviews, summarizes, and …
Fundamental limits of ridge-regularized empirical risk minimization in high dimensions
H Taheri, R Pedarsani… - … Conference on Artificial …, 2021 - proceedings.mlr.press
Despite the popularity of Empirical Risk Minimization (ERM) algorithms, a theory that
explains their statistical properties in modern high-dimensional regimes is only recently …
explains their statistical properties in modern high-dimensional regimes is only recently …
A new central limit theorem for the augmented ipw estimator: Variance inflation, cross-fit covariance and beyond
Estimation of the average treatment effect (ATE) is a central problem in causal inference. In
recent times, inference for the ATE in the presence of high-dimensional covariates has been …
recent times, inference for the ATE in the presence of high-dimensional covariates has been …
Algorithmic analysis and statistical estimation of SLOPE via approximate message passing
SLOPE is a relatively new convex optimization procedure for high-dimensional linear
regression via the sorted ℓ 1 penalty: the larger the rank of the fitted coefficient, the larger the …
regression via the sorted ℓ 1 penalty: the larger the rank of the fitted coefficient, the larger the …