output
20072025
most citedFree-electron properties of metals under ultrafast laser-induced electron-phonon nonequilibrium: A first-principles study

125 citations

Showing stat.MLShow all

8 papers · 1 filter

stat.ML2025

PAC-Bayesian Bounds on Constrained f-Entropic Risk Measures

Hind Atbir, Farah Cherfaoui, Guillaume Metzler +2

PAC generalization bounds on the risk, when expressed in terms of the expected loss, are often insufficient to capture imbalances between subgroups in the data. To overcome this li…

stat.ML2024

Leveraging PAC-Bayes Theory and Gibbs Distributions for Generalization Bounds with Complexity Measures

Paul Viallard, Rémi Emonet, Amaury Habrard +2

In statistical learning theory, a generalization bound usually involves a complexity measure imposed by the considered theoretical framework. This limits the scope of such bounds,…

stat.ML2019

Learning Landmark-Based Ensembles with Random Fourier Features and Gradient Boosting

Léo Gautheron, Pascal Germain, Amaury Habrard +3

We propose a Gradient Boosting algorithm for learning an ensemble of kernel functions adapted to the task at hand. Unlike state-of-the-art Multiple Kernel Learning techniques that…

stat.ML2015

An Improvement to the Domain Adaptation Bound in a PAC-Bayesian context

Pascal Germain, Amaury Habrard, Francois Laviolette +1

This paper provides a theoretical analysis of domain adaptation based on the PAC-Bayesian theory. We propose an improvement of the previous domain adaptation bound obtained by Germ…

stat.ML20153 cited

On Generalizing the C-Bound to the Multiclass and Multi-label Settings

Francois Laviolette, Emilie Morvant, Liva Ralaivola +1

The C-bound, introduced in Lacasse et al., gives a tight upper bound on the risk of a binary majority vote classifier. In this work, we present a first step towards extending this…

stat.ML2014

Domain adaptation of weighted majority votes via perturbed variation-based self-labeling

Emilie Morvant

In machine learning, the domain adaptation problem arrives when the test (target) and the train (source) data are generated from different distributions. A key applied issue is thu…