collaborators

6 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…

math.DS2026

Centre manifold theorem for maps along manifolds of fixed points

Lachlan Ewen MacDonald

We prove a centre manifold theorem for a map along a manifold-with-boundary of fixed points, and provide an application to the study of gradient descent with large step size on two…

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…

math.PR2025

Disintegration theorem for multifunctions, with applications to empirical Wasserstein distances and average-case statistical bounds

James Allen Fill, Lachlan Ewen MacDonald

We prove a generalisation of the disintegration theorem to the setting of multifunctions between Polish probability spaces. Whereas the classical disintegration theorem guarantees…

cs.LG2025

Understanding the Learning Dynamics of LoRA: A Gradient Flow Perspective on Low-Rank Adaptation in Matrix Factorization

Ziqing Xu, Hancheng Min, Lachlan Ewen MacDonald +4

Despite the empirical success of Low-Rank Adaptation (LoRA) in fine-tuning pre-trained models, there is little theoretical understanding of how first-order methods with carefully c…