collaborators

8 papers

cs.LG2026

Dynamics of Gradient Descent with Large Step Size Near a Manifold of Flat Minima

Lachlan Ewen MacDonald, René Vidal

An important quantity in the theory of gradient descent (GD) is the \emph{sharpness}, defined as the largest eigenvalue of the objective Hessian. Classical analyses typically requi…

stat.ML2026

SGD at the Edge of Stability: Stochastic Stabilization with Large Learning Rates

Konstantinos Emmanouilidis, Lachlan MacDonald, Salma Tarmoun +1

Modern deep learning has been shown to operate at the edge of stability, routinely using learning rates far larger than those justified by classical optimization theory. Most prior…

cs.LG2026

Transformers Learn the Optimal DDPM Denoiser for Multi-Token GMMs

Hongkang Li, Hancheng Min, Rene Vidal

Transformer-based diffusion models have demonstrated remarkable performance at generating high-quality samples. However, our theoretical understanding of the reasons for this succe…

cs.LG2025

Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data

Hancheng Min, Zhihui Zhu, René Vidal

Among many mysteries behind the success of deep networks lies the exceptional discriminative power of their learned representations as manifested by the intriguing Neural Collapse…

cs.LG2025

Convergence Rates for Gradient Descent on the Edge of Stability in Overparametrised Least Squares

Lachlan Ewen MacDonald, Hancheng Min, Leandro Palma +3

Classical optimisation theory guarantees monotonic objective decrease for gradient descent (GD) when employed in a small step size, or ``stable", regime. In contrast, gradient desc…

cs.LG2025

Understanding Incremental Learning with Closed-form Solution to Gradient Flow on Overparamerterized Matrix Factorization

Hancheng Min, René Vidal

Many theoretical studies on neural networks attribute their excellent empirical performance to the implicit bias or regularization induced by first-order optimization algorithms wh…