Logo University of Warwick

I am currently a 4th year Masters of Engineering Discrete Mathematics student at the University of Warwick. I find particularly enjoyable the process of applying my knowledge of algorithms and mathematics to solve deep and fascinating problems, creating something new and unexplored, and collaborating with a team to discover something amazing!

I have a broad interest in all of:

  • Automata and formal languages
  • Logic and games
  • Computational complexity
  • Discrete mathematics
  • Axiomatic set theory
  • Theoretical machine learning

I am currently looking for a PhD position within these interests, so if you are interested in supervising such a project, email me.

GitHub
Education
  • University of Warwick
    University of Warwick

    Masters of Engineering, Discrete Mathematics
    1st Year: 85.2%
    2nd Year: 88.1% (awarded for highest)
    3rd Year: 88.3% (awarded for project)
    All are a high first, >70% is a first.

    Sep. 2021 - present
  • Ashby School
    Ashby School
    A levels
    Computer Science:   A*
    Maths: A*
    Further Maths: A*
    Physics: A*
    Sep. 2019 - Jul. 2021
  • Ashby School
    Ashby School
    Level 2 Certificate in Further Maths (A^ top grade)
    10 GCSEs incl. Computer Science (8), Maths (9), Design and Technology (9), Physics (9), English Language (7) overall (3x 9, 2x 8, 3x 7, 2x 5)
    Sep. 2017 - Jul. 2019
Experience
  • University of Warwick - URSS Research Project
    University of Warwick - URSS Research Project
    AI Researcher
    July. 2024 - Sep. 2024
  • Rolls Royce
    Rolls Royce
    Software Development Work Experience
    Aug 2021
  • Rolls Royce
    Rolls Royce
    Work Experience Week
    June 2019
Honors & Awards
  • University of Warwick - Outstanding Department of Computer Science Third-Year Project Prize
    2024
  • University of Warwick - Exceptional achievement in the second year for Discrete Maths
    2023
  • Ashby School - Outstanding achievement in computer science
    2019
Selected Projects (view all )
Investigating the Gradient Descent of Neural Networks at the Edge of Stability
Investigating the Gradient Descent of Neural Networks at the Edge of Stability

Jonathan Auton, Ranko Lazic, Matthias Englert

URSS Showcase 2024

Artificial neural networks are a type of self-learning computer algorithm that have become central to the development of modern AI systems. The most used self-learning technique is gradient descent, a simple yet effective algorithm that iteratively improves a network by tweaking it repeatedly in a direction of improving accuracy. However, new findings suggest the step size cannot be made small enough to avoid the effects of iterative instability. As a result, the learning process tends to become chaotic and unpredictable. What is fascinating about this chaotic nature is that despite it, gradient descent still finds effective solutions. My project seeks to develop an understanding of the underlying mechanisms of this chaotic nature that is paradoxically effective.

[Poster]

Investigating the Gradient Descent of Neural Networks at the Edge of Stability

Jonathan Auton, Ranko Lazic, Matthias Englert

URSS Showcase 2024

Artificial neural networks are a type of self-learning computer algorithm that have become central to the development of modern AI systems. The most used self-learning technique is gradient descent, a simple yet effective algorithm that iteratively improves a network by tweaking it repeatedly in a direction of improving accuracy. However, new findings suggest the step size cannot be made small enough to avoid the effects of iterative instability. As a result, the learning process tends to become chaotic and unpredictable. What is fascinating about this chaotic nature is that despite it, gradient descent still finds effective solutions. My project seeks to develop an understanding of the underlying mechanisms of this chaotic nature that is paradoxically effective.

[Poster]

Interactive Exploration of 4D Fractal Orbits
Interactive Exploration of 4D Fractal Orbits

Jonathan Auton, Marcin Jurdzinski

Master's Dissertation 2024

A Java software application for rendering a 4D representation of the Mandelbrot set. The project uses novel 4D projectional techniques to efficiently visualise and move in the space, and generalises well to alternate formulae for fractal generation.

[Repo]

Interactive Exploration of 4D Fractal Orbits

Jonathan Auton, Marcin Jurdzinski

Master's Dissertation 2024

A Java software application for rendering a 4D representation of the Mandelbrot set. The project uses novel 4D projectional techniques to efficiently visualise and move in the space, and generalises well to alternate formulae for fractal generation.

[Repo]

All projects