3 papers
stat.ML2026
ResNets of All Shapes and Sizes: Convergence of Training Dynamics in the Large-scale Limit
Louis-Pierre Chaintron, Lénaïc Chizat, Javier Maass
We establish convergence of the training dynamics of residual neural networks (ResNets) to their joint infinite depth L, hidden width M, and embedding dimension D limit. Specifical…
cs.LG2025
Phase Diagram of Dropout for Two-Layer Neural Networks in the Mean-Field Regime
Lénaïc Chizat, Pierre Marion, Yerkin Yesbay
Dropout is a standard training technique for neural networks that consists of randomly deactivating units at each step of their gradient-based training. It is known to improve perf…
cs.LG2025
The Hidden Width of Deep ResNets: Tight Error Bounds and Phase Diagram
Lénaïc Chizat
We study the gradient-based training of large-depth residual networks (ResNets) from standard random initializations. We show that infinite-depth ResNets behave as if they were inf…