Cover Image

Breaking the curse of dimensionality for linear rules: optimal predictors over the ellipsoid

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ayme, Alexis, Loureiro, Bruno
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Handling Covariate Mismatch in Federated Linear Prediction
by: Ayme, Alexis, et al.
Published: (2026)

On the existence of consistent adversarial attacks in high-dimensional linear classification
by: Vilucchio, Matteo, et al.
Published: (2025)

Breaking the curse of dimensionality in structured density estimation
by: Vandermeulen, Robert A., et al.
Published: (2024)

Does the Barron space really defy the curse of dimensionality?
by: Schavemaker, Olov
Published: (2025)

Random features models: a way to study the success of naive imputation
by: Ayme, Alexis, et al.
Published: (2024)

Conformal prediction for multi-dimensional time series by ellipsoidal sets
by: Xu, Chen, et al.
Published: (2024)

Escaping mediocrity: how two-layer networks learn hard generalized linear models with SGD
by: Arnaboldi, Luca, et al.
Published: (2023)

The curse of random quantum data
by: Zhang, Kaining, et al.
Published: (2024)

Score-based generative models break the curse of dimensionality in learning a family of sub-Gaussian probability distributions
by: Cole, Frank, et al.
Published: (2024)

Learning minimal volume uncertainty ellipsoids
by: Alon, Itai, et al.
Published: (2024)

Universality laws for Gaussian mixtures in generalized linear models
by: Dandi, Yatin, et al.
Published: (2023)

Kernel ridge regression under power-law data: spectrum and generalization
by: Wortsman, Arie, et al.
Published: (2025)

MOCA-HESP: Meta High-dimensional Bayesian Optimization for Combinatorial and Mixed Spaces via Hyper-ellipsoid Partitioning
by: Ngo, Lam, et al.
Published: (2025)

Sharp description of local minima in the loss landscape of high-dimensional two-layer ReLU neural networks
by: Huang, Jie, et al.
Published: (2026)

Annealing in variational inference mitigates mode collapse: A theoretical study on Gaussian mixtures
by: Fogliani, Luigi, et al.
Published: (2026)

Bilinear representation mitigates reversal curse and enables consistent model editing
by: Kim, Dong-Kyum, et al.
Published: (2025)

Bayes optimal learning in high-dimensional linear regression with network side information
by: Nandy, Sagnik, et al.
Published: (2023)

High-dimensional robust regression under heavy-tailed data: Asymptotics and Universality
by: Adomaityte, Urte, et al.
Published: (2023)

Analysis of Bootstrap and Subsampling in High-dimensional Regularized Regression
by: Clarté, Lucas, et al.
Published: (2024)

The curse of overparametrization in adversarial training: Precise analysis of robust generalization for random features regression
by: Hassani, Hamed, et al.
Published: (2022)

Optimal scaling laws in learning hierarchical multi-index models
by: Defilippis, Leonardo, et al.
Published: (2026)

A Noise Sensitivity Exponent Controls Large Statistical-to-Computational Gaps in Single- and Multi-Index Models
by: Defilippis, Leonardo, et al.
Published: (2026)

On the optimal regret of collaborative personalized linear bandits
by: Huang, Bruce, et al.
Published: (2025)

Transformers are almost optimal metalearners for linear classification
by: Magen, Roey, et al.
Published: (2025)

Deflated HeteroPCA: Overcoming the curse of ill-conditioning in heteroskedastic PCA
by: Zhou, Yuchen, et al.
Published: (2023)

Interpretable non-linear dimensionality reduction using gaussian weighted linear transformation
by: Bergh, Erik
Published: (2025)

Fast Escape, Slow Convergence: Learning Dynamics of Phase Retrieval under Power-Law Data
by: Braun, Guillaume, et al.
Published: (2025)

How does feature learning reshape the function space?
by: Lobo, João, et al.
Published: (2026)

Hybrid safe-strong rules for efficient optimization in lasso-type problems
by: Zeng, Yaohui, et al.
Published: (2017)

Dimension-free deterministic equivalents and scaling laws for random feature regression
by: Defilippis, Leonardo, et al.
Published: (2024)

Fundamental computational limits of weak learnability in high-dimensional multi-index models
by: Troiani, Emanuele, et al.
Published: (2024)

How Two-Layer Neural Networks Learn, One (Giant) Step at a Time
by: Dandi, Yatin, et al.
Published: (2023)

A Random Matrix Theory of Masked Self-Supervised Regression
by: Zurich, Arie Wortsman, et al.
Published: (2026)

Fitting an ellipsoid to a quadratic number of random points
by: Bandeira, Afonso S., et al.
Published: (2023)

Adversarial bandit optimization for approximately linear functions
by: Cheng, Zhuoyu, et al.
Published: (2025)

Conditioning non-linear and infinite-dimensional diffusion processes
by: Baker, Elizabeth Louise, et al.
Published: (2024)

Improving sample efficiency of high dimensional Bayesian optimization with MCMC
by: Yi, Zeji, et al.
Published: (2024)

Online Learning and Information Exponents: On The Importance of Batch size, and Time/Complexity Tradeoffs
by: Arnaboldi, Luca, et al.
Published: (2024)

Mitigating over-exploration in latent space optimization using LES
by: Ronen, Omer, et al.
Published: (2024)

Sparse Polyak: an adaptive step size rule for high-dimensional M-estimation
by: Qiao, Tianqi, et al.
Published: (2025)