Publications

  • Baptiste Bauvin, Cécile Capponi, Jean-Francis Roy, and François Laviolette. Fast greedy c-bound minimization with guarantees. Machine Learning, pages 1–42, 2020. [ Bibtex ]
  • Luc Bégin, Pascal Germain, François Laviolette, and Jean-Francis Roy. Pac-bayesian theory for transductive learning. In Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, 105–113. 2014. [ Bibtex ]
  • Luc Bégin, Pascal Germain, François Laviolette, and Jean-Francis Roy. Pac-bayesian bounds based on the rényi divergence. In Proceedings of the Nineteenth International Conference on Artificial Intelligence and Statistics, 435–444. 2016. [ Bibtex ]
  • Pascal Germain, Sébastien Giguère, Jean-Francis Roy, Brice Zirakiza, François Laviolette, and Claude-Guy Quimper. A pseudo-boolean set covering machine. In Proceedings of the 18th International Conference on Principles and Practice of Constraint Programming, CP 2012, Québec, Canada, 916–924. 2012. [ Bibtex ]
  • Pascal Germain, Alexandre Lacasse, François Laviolette, Mario Marchand, and Jean-Francis Roy. Risk bounds for the majority vote: from a pac-bayesian analysis to a learning algorithm. Journal of Machine Learning Research, pages 787–860, 2015. [ Bibtex ]
  • François Laviolette, Emilie Morvant, Liva Ralaivola, and Jean-Francis Roy. Risk upper bounds for general ensemble methods with an application to multiclass classification. Neurocomputing, 219:15–25, 2017. [ Bibtex ]
  • François Laviolette, Mario Marchand, and Jean-Francis Roy. From pac-bayes bounds to quadratic programs for majority votes. In Proceedings of the 28th International Conference on Machine Learning, ICML 2011, Bellevue, Washington, USA, 649–656. 2011. [ Bibtex ]
  • François Laviolette, Mario Marchand, and Jean-Francis Roy. Cqboost: a column generation methode for minimizing the c-bound. In NIPS Workshop on Optimization for Machine Learning. 2014. [ Bibtex ]
  • François Laviolette, Emilie Morvant, Liva Ralaivola, and Jean-Francis Roy. On generalizing the c-bound to the multiclass and multi-label settings. In NIPS Workshop on Representation and Learning Methods for Complex Outputs. 2014. [ Bibtex ]
  • Jean-Francis Roy, Mario Marchand, and François Laviolette. A column generation bound minimization approach with pac-bayesian generalization guarantees. In Proceedings of the Nineteenth International Conference on Artificial Intelligence and Statistics, 1241–1249. 2016. [ Bibtex ]