Lenka Zdeborová

5 papers EPFL

• Asymptotics of SGD in Sequence-Single Index Models and Single-Layer Attention Networks
• Bayes optimal learning of attention-indexed models
• Learning with Restricted Boltzmann Machines: Asymptotics of AMP and GD in High Dimensions
• The Computational Advantage of Depth in Learning High-Dimensional Hierarchical Targets
• The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks