1 citations · 1 across the 4 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Long-time dynamics and universality of nonconvex gradient descent
Qiyang Han
This paper develops a general approach to characterize the long-time trajectory behavior of nonconvex gradient descent in generalized single-index models in the large aspect ratio…
cs.LG2025
Precise gradient descent training dynamics for finite-width multi-layer neural networks
Qiyang Han, Masaaki Imaizumi
In this paper, we provide the first precise distributional characterization of gradient descent iterates for general multi-layer neural networks under the canonical single-index re…