Cover Image

On the necessity of adaptive regularisation:Optimal anytime online learning on $\boldsymbol{\ell_p}$-balls

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Johnson, Emmeran, Martínez-Rubio, David, Pike-Burke, Ciara, Rebeschini, Patrick
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

Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity
by: Johnson, Emmeran, et al.
Published: (2023)

Stochastic Shortest Path with Sparse Adversarial Costs
by: Johnson, Emmeran, et al.
Published: (2025)

Manifold-regularised Large-Margin $\ell_p$-SVDD for Multidimensional Time Series Anomaly Detection
by: Arashloo, Shervin Rahimzadeh
Published: (2025)

Optimality of Matrix Mechanism on $\ell_p^p$-metric
by: Liu, Jingcheng, et al.
Published: (2024)

Fixed-Confidence Multiple Change Point Identification under Bandit Feedback
by: Lazzaro, Joseph, et al.
Published: (2025)

Fixed-Budget Change Point Identification in Piecewise Constant Bandits
by: Lazzaro, Joseph, et al.
Published: (2025)

Coresets for Multiple $\ell_p$ Regression
by: Woodruff, David P., et al.
Published: (2024)

When and why randomised exploration works (in linear bandits)
by: Abeille, Marc, et al.
Published: (2025)

Optimal bounds for $\ell_p$ sensitivity sampling via $\ell_2$ augmentation
by: Munteanu, Alexander, et al.
Published: (2024)

Sharper Bounds for $\ell_p$ Sensitivity Sampling
by: Woodruff, David P., et al.
Published: (2023)

On Traceability in $\ell_p$ Stochastic Convex Optimization
by: Voitovych, Sasha, et al.
Published: (2025)

Locally Differentially Private Thresholding Bandits
by: Barbara, Annalisa, et al.
Published: (2025)

QuACK: A Multipurpose Queuing Algorithm for Cooperative $k$-Armed Bandits
by: Howson, Benjamin, et al.
Published: (2024)

Learning Fair And Effective Points-Based Rewards Programs
by: Hssaine, Chamsi, et al.
Published: (2025)

Ridge Leverage Score Sampling for $\ell_p$ Subspace Approximation
by: Woodruff, David P., et al.
Published: (2024)

Turnstile $\ell_p$ leverage score sampling with applications
by: Munteanu, Alexander, et al.
Published: (2024)

Iterative Refinement for $\ell_p$-norm Regression
by: Adil, Deeksha, et al.
Published: (2019)

Exploring Sparsity and Smoothness of Arbitrary $\ell_p$ Norms in Adversarial Attacks
by: Duhme, Christof, et al.
Published: (2026)

Beyond $\ell_2$-norm and $\ell_\infty$-norm: A Curvature-Inspired $\ell_p$-Norm Scheme for Deep Neural Networks
by: Xu, Jianhao, et al.
Published: (2026)

Strange shadows of $\ell_p$-balls
by: Kabluchko, Zakhar, et al.
Published: (2024)

Black-Box Uniform Stability for Non-Euclidean Empirical Risk Minimization
by: Vary, Simon, et al.
Published: (2024)

Robust Gradient Descent for Phase Retrieval
by: Buna, Alex, et al.
Published: (2024)

Towards An Efficient Approach for the Nonconvex $\ell_p$ Ball Projection: Algorithm and Analysis
by: Yang, Xiangyu, et al.
Published: (2021)

Stacey: Promoting Stochastic Steepest Descent via Accelerated $\ell_p$-Smooth Nonconvex Optimization
by: Luo, Xinyu, et al.
Published: (2025)

Online Correlation Clustering: Simultaneously Optimizing All $\ell_p$-norms
by: Davies, Sami, et al.
Published: (2025)

Time-sensitive anytime-valid testing
by: Clerico, Eugenio, et al.
Published: (2026)

Radii of Euclidean sections of $\ell_p$-balls
by: Szarek, Stanislaw, et al.
Published: (2024)

Softmax is $1/2$-Lipschitz: A tight bound across all $\ell_p$ norms
by: Nair, Pravin
Published: (2025)

De-singularity Subgradient for the $q$-th-Powered $\ell_p$-Norm Weber Location Problem
by: Lai, Zhao-Rong, et al.
Published: (2024)

Closed-form $\ell_r$ norm scaling with data for overparameterized linear regression and diagonal linear networks under $\ell_p$ bias
by: Zhang, Shuofeng, et al.
Published: (2025)

Best-of-Both Worlds for linear contextual bandits with paid observations
by: Boyer, Nathan, et al.
Published: (2025)

Adaptive auditing of AI systems with anytime-valid guarantees
by: Zhou, Siyu, et al.
Published: (2026)

Sharp Risk Bounds for Early-Stopping in Gaussian Linear Regression
by: Wegel, Tobias, et al.
Published: (2025)

Active, anytime-valid risk controlling prediction sets
by: Xu, Ziyu, et al.
Published: (2024)

PowerStep: Memory-Efficient Adaptive Optimization via $\ell_p$-Norm Steepest Descent
by: Lu, Yao, et al.
Published: (2026)

Differentiable Cost-Parameterized Monge Map Estimators
by: Howard, Samuel, et al.
Published: (2024)

A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence
by: Alfano, Carlo, et al.
Published: (2023)

Complexity of Classical Acceleration for $\ell_1$-Regularized PageRank
by: Fountoulakis, Kimon, et al.
Published: (2026)

Self-Concordant Perturbations for Linear Bandits
by: Lévy, Lucas, et al.
Published: (2025)

Revisiting mean estimation over $\ell_p$ balls: Is the MLE optimal?
by: Aolaritei, Liviu, et al.
Published: (2025)