Laura Harkins

About Me

I am a PhD student at the Department of Computer Science at the University of Warwick supervised by Matthias Englert. My research explores the implicit bias of gradient descent on ReLU networks and is being funded by the Engineering and Physical Sciences Research Council (EPSRC). I am the Head of Education at Warwick's AI society and a member of the Centre for Discrete Mathematics and its Applications (DIMAP). Prior to starting my PhD, I graduated from the University of Warwick in 2024 with a First Class Masters of Engineering in Discrete Mathematics.

Research Interests

In the broadest sense I am interested in the theoretical understanding of machine learning. This includes: the learning dynamics of neural networks, implicit bias of gradient descent and regularizers, and the existance of adversarial examples in trained neural networks.

Publications

Minimally Sharp Interpolators have Minimal Norm, are Sparse, and Overfit Temperately - (Work in Progress)

Teaching

I have been a teaching assistant for the following modules:

2024/2025

• CS260 Algorithms
• CS262 Logic and Verification

2025/2026