Allauzen, Alexandre

12 publications

ICLR 2025 Accelerated Training Through Iterative Gradient Propagation Along the Residual Path Erwan Fagnou, Paul Caillon, Blaise Delattre, Alexandre Allauzen

AISTATS 2025 Bridging the Theoretical Gap in Randomized Smoothing Blaise Delattre, Paul Caillon, Quentin Barthélemy, Erwan Fagnou, Alexandre Allauzen

TMLR 2025 Differentially Private Gradient Flow Based on the Sliced Wasserstein Distance Ilana Sebag, Muni Sreenivas Pydi, Jean-Yves Franceschi, Alain Rakotomamonjy, Mike Gartrell, Jamal Atif, Alexandre Allauzen

ICML 2025 Improving Diversity in Language Models: When Temperature Fails, Change the Loss Alexandre Verine, Florian Le Bronnec, Kunhao Zheng, Alexandre Allauzen, Yann Chevaleyre, Benjamin Negrevergne

ICLR 2025 SCOPE: A Self-Supervised Framework for Improving Faithfulness in Conditional Text Generation Song Duong, Florian Le Bronnec, Alexandre Allauzen, Vincent Guigue, Alberto Lumbreras, Laure Soulier, Patrick Gallinari

ICLR 2024 The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing Blaise Delattre, Alexandre Araujo, Quentin Barthélemy, Alexandre Allauzen

ICLR 2023 A Unified Algebraic Perspective on Lipschitz Neural Networks Alexandre Araujo, Aaron J Havens, Blaise Delattre, Alexandre Allauzen, Bin Hu

ICML 2023 Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration Blaise Delattre, Quentin Barthélemy, Alexandre Araujo, Alexandre Allauzen

MLJ 2023 Relational Data Embeddings for Feature Enrichment with Background Information Alexis Cvetkov-Iliev, Alexandre Allauzen, Gaël Varoquaux

ICML 2022 A Dynamical System Perspective for Lipschitz Neural Networks Laurent Meunier, Blaise J Delattre, Alexandre Araujo, Alexandre Allauzen

NeurIPSW 2022 Experimental Study of Neural ODE Training with Adaptive Solver for Dynamical Systems Modeling Alexandre Allauzen, Thiago Petrilli Maffei Dardis, Hannah Plath

JMLR 2017 Document Neural Autoregressive Distribution Estimation Stanislas Lauly, Yin Zheng, Alexandre Allauzen, Hugo Larochelle