no code implementations • 12 May 2020 • Borja Rodríguez-Gálvez, Germán Bassi, Mikael Skoglund
In this work, we study the generalization capability of algorithms from an information-theoretic perspective.
2 code implementations • 11 Jun 2020 • Borja Rodríguez-Gálvez, Ragnar Thobaben, Mikael Skoglund
In this article, we propose a new variational approach to learn private and/or fair representations.
no code implementations • 21 Oct 2020 • Borja Rodríguez-Gálvez, Germán Bassi, Ragnar Thobaben, Mikael Skoglund
In this work, we unify several expected generalization error bounds based on random subsets using the framework developed by Hellstr\"om and Durisi [1].
no code implementations • NeurIPS 2021 • Borja Rodríguez-Gálvez, Germán Bassi, Ragnar Thobaben, Mikael Skoglund
This work presents several expected generalization error bounds based on the Wasserstein distance.
no code implementations • 17 Sep 2021 • Borja Rodríguez-Gálvez, Filip Granqvist, Rogier Van Dalen, Matt Seigel
This paper introduces an algorithm to enforce group fairness in private federated learning, where users' data does not leave their devices.
no code implementations • 18 Jul 2022 • Amaury Gouverneur, Borja Rodríguez-Gálvez, Tobias J. Oechtering, Mikael Skoglund
Building on the framework introduced by Xu and Raginksy [1] for supervised learning problems, we study the best achievable performance for model-based Bayesian reinforcement learning problems.
no code implementations • 27 Dec 2022 • Mahdi Haghifam, Borja Rodríguez-Gálvez, Ragnar Thobaben, Mikael Skoglund, Daniel M. Roy, Gintare Karolina Dziugaite
To date, no "information-theoretic" frameworks for reasoning about generalization error have been shown to establish minimax rates for gradient descent in the setting of stochastic convex optimization.
no code implementations • 26 Apr 2023 • Amaury Gouverneur, Borja Rodríguez-Gálvez, Tobias J. Oechtering, Mikael Skoglund
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 information ratio.
no code implementations • 21 Jun 2023 • Borja Rodríguez-Gálvez, Ragnar Thobaben, Mikael Skoglund
Firstly, for losses with a bounded range, we recover a strengthened version of Catoni's bound that holds uniformly for all parameter values.
1 code implementation • 20 Jul 2023 • Borja Rodríguez-Gálvez, Arno Blaas, Pau Rodríguez, Adam Goliński, Xavier Suau, Jason Ramapuram, Dan Busbridge, Luca Zappella
We consider a different lower bound on the MI consisting of an entropy and a reconstruction term (ER), and analyze the main MVSSL families through its lens.
no code implementations • 5 Mar 2024 • Amaury Gouverneur, Borja Rodríguez-Gálvez, Tobias J. Oechtering, Mikael Skoglund
This paper studies the Bayesian regret of a variant of the Thompson-Sampling algorithm for bandit problems.
no code implementations • 25 Mar 2024 • Borja Rodríguez-Gálvez, Omar Rivasplata, Ragnar Thobaben, Mikael Skoglund
Moreover, the paper derives a high-probability PAC-Bayes bound for losses with a bounded variance.