activity
20242026
collaborators
Showing stat.MLShow all

7 papers · 1 filter

stat.ML2026

Minimax Optimal Early-Stopped Gradient Descent for Gaussian Mixture Classification

Alex Buna, Shirley Xiaoqi Liu, Patrick Rebeschini

In overparameterised classification, training data can be linearly separable even when the underlying distribution is not. In this setting, gradient descent (GD) on the logistic lo…

stat.ML2026

Self-Concordant Perturbations for Linear Bandits

Lucas Lévy, Jean-Lou Valeau, Arya Akhavan +1

We consider the adversarial linear bandits setting and present a unified algorithmic framework that bridges Follow-the-Regularized-Leader (FTRL) and Follow-the-Perturbed-Leader (FT…

stat.ML2026

Generalization in Nonlinear Least Squares via Learned Feature Geometry

Ayub Kharel, Ilja Kuzborskij, Patrick Rebeschini +1

We study the generalization of ridge-regularized nonlinear least-squares models via on-average algorithmic stability, deriving error bounds for local minimizers in terms of a data-…

stat.ML2026

Learning mirror maps in policy mirror descent

Carlo Alfano, Sebastian Towers, Silvia Sapora +2

Policy Mirror Descent (PMD) is a popular framework in reinforcement learning, serving as a unifying perspective that encompasses numerous algorithms. These algorithms are derived t…

stat.ML2025

Non-stationary Bandit Convex Optimization: A Comprehensive Study

Xiaoqi Liu, Dorian Baudry, Julian Zimmert +2

Bandit Convex Optimization is a fundamental class of sequential decision-making problems, where the learner selects actions from a continuous domain and observes a loss (but not it…

stat.ML2025

Implicit Regularisation in Diffusion Models: An Algorithm-Dependent Generalisation Analysis

Tyler Farghly, Patrick Rebeschini, George Deligiannidis +1

The success of denoising diffusion models raises important questions regarding their generalisation behaviour, particularly in high-dimensional settings. Notably, it has been shown…