Researcher profile
François‐Xavier Vialard
2 papers in the PaperMetrix corpus
Publications
Papers by this author
-
Understanding the training of infinitely deep and wide ResNets with conditional optimal transport
2025 · Communications on Pure and Applied Mathematics
Abstract We study the convergence of gradient flow for the training of deep neural networks. While residual neural networks (ResNet) are a popular example of very deep architectures, their training constitutes a challenging optimization problem, …
-
Token Sample Complexity of Attention
2025 · arXiv (Cornell University)
As context windows in large language models continue to expand, it is essential to characterize how attention behaves at extreme sequence lengths. We introduce token sample complexity: the rate at which attention computed on $n$ …