Yaiza Bermudez | INRIA | Publications

Conference Papers

• “Machine Unlearning for Gibbs Supervised Learning Algorithms”, with Samir Perlaza and Iñaki Esnaola.
  In Proc. of the IEEE International Symposium on Information Theory (ISIT), Guangzhou, China, Jun., 2026.
  Finalist for the Jack Keil Wolf ISIT Student Paper Award.

• “Decentralized Machine Learning with Centralized Performance Guarantees via Gibbs Algorithms”, with Samir Perlaza and Iñaki Esnaola.
  In Proc. of the IEEE International Symposium on Information Theory (ISIT), Guangzhou, China, Jun., 2026.

• “Equivalence of Optimal Transport Problems to Regularization on the Family of f-Divergences”, with Maxime Nicaise and Samir Perlaza.
  In Proc. of the IEEE International Symposium on Information Theory (ISIT), Guangzhou, China, Jun., 2026.

• “Démonstrations des théorèmes folkloriques sur la dérivée de Radon-Nikodym”, with Gaetan Bisson, Iñaki Esnaola and Samir Perlaza.
  In Proc. of the XXXe Colloque Francophone de Traitement du Signal et des Images (GRETSI), Strasbourg, France, Aug., 2025.

• “Incremental learning for load forecasting in energy networks and buildings”, with Mathieu Vallée, Mohammed Ali Jallal and Marina Reyboz.
  In Proc. of the 38th International Conference on Efficiency, Cost, Optimization, Simulation and Environmental Impact of Energy Systems (ECOS), Paris, France, Jun., 2025.

• “Lightweight hybrid local PV short term forecasting using both physics and data”, with Benoit Delinchant, Vincent Imard, and Frédéric Wurtz.
  In Proc. of the 15th Asia-Pacific Power and Energy Engineering Conference (APPEEC),Chiang Mai, Thailand, Dec., 2023.

Research Reports

• ‘‘A Gauge-Fixed Sinkhorn Algorithm for Semi-Relaxed Optimal Transport", with Maxime Nicaise and Samir Perlaza.
  Research Report, INRIA, No. RR-9615, Sophia Antipolis, France, May, 2026.

• ‘‘Equivalence Between Nested Gibbs Measures and Log-Linear Combinations of Gibbs Measures", with Samir Perlaza and Iñaki Esnaola.
  Research Report, INRIA, No. RR-9613, Sophia Antipolis, France, May, 2026.

• ‘‘Machine Unlearning for Gibbs Supervised Learning Algorithms", with Samir Perlaza and Iñaki Esnaola.
  Research Report, INRIA, No. RR-9610, Sophia Antipolis, France, Jan., 2026.

• ‘‘Decentralized Machine Learning with Centralized Performance Guarantees via Gibbs Algorithms", with Samir Perlaza and Iñaki Esnaola.
  Research Report, INRIA, No. RR-9608, Sophia Antipolis, France, Jan., 2026.

• ‘‘On optimal transport with f-divergence regularization", with Maxime Nicaise and Samir Perlaza.
  Research Report, INRIA, No. RR-9607, Sophia Antipolis, France, Jan., 2026.

• “Statistical Federated Learning and Generalization”, with Samir Perlaza, Iñaki Esnaola and H. Vincent Poor.
  Research Report, INRIA, No. RR-9599, Sophia Antipolis, France, Oct., 2025.

• “Proofs for Folklore Theorems on the Radon-Nikodym Derivative”, with Gaetan Bisson, Iñaki Esnaola and Samir Perlaza.
  Research Report, INRIA, No. RR-9591, Sophia Antipolis, France, July, 2025.

Journal Papers

• ‘‘Equivalence of Optimal Transport Problems to Regularization on the Family of f-Divergence", with Maxime Nicaise and Samir Perlaza.
  Submitted to Information and Inference: A Journal of the IMA, on February 12, 2026.