30 citations · 99 across the 7 of their papers we have counts for
8 papers
More PAC-Bayes bounds: From bounded losses, to losses with general tail behaviors, to anytime validity
Borja Rodríguez-Gálvez, Ragnar Thobaben, Mikael Skoglund
In this paper, we present new high-probability PAC-Bayes bounds for different types of losses. Firstly, for losses with a bounded range, we recover a strengthened version of Catoni…
Thompson Sampling Regret Bounds for Contextual Bandits with sub-Gaussian rewards
Amaury Gouverneur, Borja Rodríguez-Gálvez, Tobias J. Oechtering +1
In this work, we study the performance of the Thompson Sampling algorithm for Contextual Bandit problems based on the framework introduced by Neu et al. and their concept of lifted…
Enforcing fairness in private federated learning via the modified method of differential multipliers
Borja Rodríguez-Gálvez, Filip Granqvist, Rogier van Dalen +1
Federated learning with differential privacy, or private federated learning, provides a strategy to train machine learning models while respecting users' privacy. However, differen…
Tighter expected generalization error bounds via Wasserstein distance
Borja Rodríguez-Gálvez, Germán Bassi, Ragnar Thobaben +1
This work presents several expected generalization error bounds based on the Wasserstein distance. More specifically, it introduces full-dataset, single-letter, and random-subset b…
On Random Subset Generalization Error Bounds and the Stochastic Gradient Langevin Dynamics Algorithm
Borja Rodríguez-Gálvez, Germán Bassi, Ragnar Thobaben +1
In this work, we unify several expected generalization error bounds based on random subsets using the framework developed by Hellström and Durisi [1]. First, we recover the bounds…
A Variational Approach to Privacy and Fairness
Borja Rodríguez-Gálvez, Ragnar Thobaben, Mikael Skoglund
In this article, we propose a new variational approach to learn private and/or fair representations. This approach is based on the Lagrangians of a new formulation of the privacy a…
Upper Bounds on the Generalization Error of Private Algorithms for Discrete Data
Borja Rodríguez-Gálvez, Germán Bassi, Mikael Skoglund
In this work, we study the generalization capability of algorithms from an information-theoretic perspective. It has been shown that the expected generalization error of an algorit…
The Convex Information Bottleneck Lagrangian
Borja Rodríguez-Gálvez, Ragnar Thobaben, Mikael Skoglund
The information bottleneck (IB) problem tackles the issue of obtaining relevant compressed representations of some random variable for the task of predicting . It is def…