Showing stat.MLShow all
3 papers · 1 filter
stat.ML2026
The Well-Tempered Classifier: Some Elementary Properties of Temperature Scaling
Pierre-Alexandre Mattei, Bruno Loureiro
Temperature scaling is a simple method that allows to control the uncertainty of probabilistic models. It is mostly used in two contexts: improving the calibration of classifiers a…
stat.ML2026
A Random Matrix Theory of Masked Self-Supervised Regression
Arie Wortsman Zurich, Federica Gerace, Bruno Loureiro +1
In the era of transformer models, masked self-supervised learning (SSL) has become a foundational training paradigm. A defining feature of masked SSL is that training aggregates pr…
stat.ML2025
Breaking the curse of dimensionality for linear rules: optimal predictors over the ellipsoid
Alexis Ayme, Bruno Loureiro
In this work, we address the following question: What minimal structural assumptions are needed to prevent the degradation of statistical learning bounds with increasing dimensiona…