105 citations · 490 across the 24 of their papers we have counts for
Showing stat.MLShow all
2 papers · 1 filter
stat.ML2024★ 3 cited
Asymptotics of Learning with Deep Structured (Random) Features
Dominik Schröder, Daniil Dmitriev, Hugo Cui +1
For a large class of feature maps we provide a tight asymptotic characterisation of the test error associated with learning the readout layer, in the high-dimensional limit where t…
stat.ML2021★ 2 cited
Analysis of One-Hidden-Layer Neural Networks via the Resolvent Method
Vanessa Piccolo, Dominik Schröder
In this work, we investigate the asymptotic spectral density of the random feature matrix with generated by a single-hidden-layer neural network, where $…