publications

2026

1. ICLR

   Scaling Direct Feedback Learning with Theoretical Guarantees

   Paul Caillon, Erwan Fagnou, Blaise Delattre, and 1 more author

   In International Conference on Learning Representations (ICLR), 2026

   Bib

   @inproceedings{caillon2026scaling,
     title = {Scaling Direct Feedback Learning with Theoretical Guarantees},
     author = {Caillon, Paul and Fagnou, Erwan and Delattre, Blaise and Allauzen, Alexandre},
     booktitle = {International Conference on Learning Representations (ICLR)},
     year = {2026}
   }

2025

1. arXiv

   Conditional Distribution Quantization in Machine Learning

   Blaise Delattre, Sylvain Delattre, Alexandre Vérine, and 1 more author

   arXiv preprint arXiv:2502.07151, 2025

   arXiv Bib HTML

   @article{delattre2025conditional,
     title = {Conditional Distribution Quantization in Machine Learning},
     author = {Delattre, Blaise and Delattre, Sylvain and V{\'e}rine, Alexandre and Allauzen, Alexandre},
     journal = {arXiv preprint arXiv:2502.07151},
     year = {2025},
   }

2. ICLR

   Accelerated Training through Iterative Gradient Propagation Along the Residual Path

   Erwan Fagnou, Paul Caillon, Blaise Delattre, and 1 more author

   In International Conference on Learning Representations (ICLR). Oral presentation , 2025

   Bib HTML

   @inproceedings{fagnou2025accelerated,
     title = {Accelerated Training through Iterative Gradient Propagation Along the Residual Path},
     author = {Fagnou, Erwan and Caillon, Paul and Delattre, Blaise and Allauzen, Alexandre},
     booktitle = {International Conference on Learning Representations (ICLR)},
     year = {2025},
   }

3. AISTATS

   Bridging the Theoretical Gap in Randomized Smoothing

   Blaise Delattre, Paul Caillon, Erwan Fagnou, and 2 more authors

   In The 28th International Conference on Artificial Intelligence and Statistics (AISTATS), 2025

   Bib HTML

   @inproceedings{delattre2025bridging,
     title = {Bridging the Theoretical Gap in Randomized Smoothing},
     author = {Delattre, Blaise and Caillon, Paul and Fagnou, Erwan and Barth{\'e}lemy, Quentin and Allauzen, Alexandre},
     booktitle = {The 28th International Conference on Artificial Intelligence and Statistics (AISTATS)},
     year = {2025},
   }

2024

1. ACL

   Chain and Causal Attention for Efficient Entity Tracking

   Erwan Fagnou, Paul Caillon, Blaise Delattre, and 1 more author

   In Association for Computational Linguistics (ACL), 2024

   Bib HTML

   @inproceedings{fagnou2024chain,
     title = {Chain and Causal Attention for Efficient Entity Tracking},
     author = {Fagnou, Erwan and Caillon, Paul and Delattre, Blaise and Allauzen, Alexandre},
     booktitle = {Association for Computational Linguistics (ACL)},
     year = {2024},
   }

2. arXiv

   Spectral Norm of Convolutional Layers with Circular and Zero Paddings

   Blaise Delattre, Quentin Barthélemy, and Alexandre Allauzen

   arXiv preprint arXiv:2402.00240, 2024

   arXiv Bib HTML

   @article{delattre2024spectral,
     title = {Spectral Norm of Convolutional Layers with Circular and Zero Paddings},
     author = {Delattre, Blaise and Barth{\'e}lemy, Quentin and Allauzen, Alexandre},
     journal = {arXiv preprint arXiv:2402.00240},
     year = {2024},
   }

3. ICLR

   The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing

   Blaise Delattre, Alexandre Araujo, Quentin Barthélemy, and 1 more author

   In International Conference on Learning Representations (ICLR), 2024

   Bib HTML

   @inproceedings{delattre2024lipschitz,
     title = {The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing},
     author = {Delattre, Blaise and Araujo, Alexandre and Barth{\'e}lemy, Quentin and Allauzen, Alexandre},
     booktitle = {International Conference on Learning Representations (ICLR)},
     year = {2024},
   }

2023

1. ICML

   Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration

   Blaise Delattre, Quentin Barthélemy, Alexandre Araujo, and 1 more author

   In International Conference on Machine Learning (ICML), 2023

   Bib HTML

   @inproceedings{delattre2023efficient,
     title = {Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration},
     author = {Delattre, Blaise and Barth{\'e}lemy, Quentin and Araujo, Alexandre and Allauzen, Alexandre},
     booktitle = {International Conference on Machine Learning (ICML)},
     year = {2023},
   }

2. ICLR

   A Unified Algebraic Perspective on Lipschitz Neural Networks

   Alexandre Araujo, Aaron Havens, Blaise Delattre, and 2 more authors

   In International Conference on Learning Representations (ICLR), 2023

   Bib HTML

   @inproceedings{araujo2023unified,
     title = {A Unified Algebraic Perspective on Lipschitz Neural Networks},
     author = {Araujo, Alexandre and Havens, Aaron and Delattre, Blaise and Allauzen, Alexandre and Hu, Bin},
     booktitle = {International Conference on Learning Representations (ICLR)},
     year = {2023},
   }

2022

1. ICML

   A Dynamical System Perspective for Lipschitz Neural Networks

   Laurent Meunier, Blaise Delattre, Alexandre Araujo, and 1 more author

   In International Conference on Machine Learning (ICML), 2022

   Bib HTML

   @inproceedings{meunier2022dynamical,
     title = {A Dynamical System Perspective for Lipschitz Neural Networks},
     author = {Meunier, Laurent and Delattre, Blaise and Araujo, Alexandre and Allauzen, Alexandre},
     booktitle = {International Conference on Machine Learning (ICML)},
     year = {2022},
   }