Matthew Farrugia-Roberts

According to our database, Matthew Farrugia-Roberts authored at least 10 papers between 2022 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Mitigating Goal Misgeneralization via Minimax Regret.

Karim Abdel Sadek, Matthew Farrugia-Roberts, Usman Anwar, Hannah Erlebach, Christian A. Schröder de Witt, David Krueger, Michael Dennis

CoRR, July, 2025

You Are What You Eat - AI Alignment Requires Understanding How Data Shapes Structure and Generalisation.

Simon Pepin Lehalleur, Jesse Hoogland, Matthew Farrugia-Roberts, Susan Wei, Alexander Gietelink Oldenziel, George Wang, Liam Carroll, Daniel Murfet

CoRR, February, 2025

Dynamics of Transient Structure in In-Context Linear Regression Transformers.

Liam Carroll, Jesse Hoogland, Matthew Farrugia-Roberts, Daniel Murfet

CoRR, January, 2025

Loss Landscape Degeneracy and Stagewise Development in Transformers.

Jesse Hoogland, George Wang, Matthew Farrugia-Roberts, Liam Carroll, Susan Wei, Daniel Murfet

Trans. Mach. Learn. Res., 2025

2024

The Developmental Landscape of In-Context Learning.

Jesse Hoogland, George Wang, Matthew Farrugia-Roberts, Liam Carroll, Susan Wei, Daniel Murfet

CoRR, 2024

2023

Computational Complexity of Detecting Proximity to Losslessly Compressible Neural Network Parameters.

Matthew Farrugia-Roberts

CoRR, 2023

Functional Equivalence and Path Connectivity of Reducible Hyperbolic Tangent Networks.

Matthew Farrugia-Roberts

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Invariance in Policy Optimisation and Partial Identifiability in Reward Learning.

Joar Max Viktor Skalse, Matthew Farrugia-Roberts, Stuart Russell, Alessandro Abate, Adam Gleave

Proceedings of the International Conference on Machine Learning, 2023

2022

Teaching Simple Constructive Proofs with Haskell Programs.

Matthew Farrugia-Roberts, Bryn Jeffries, Harald Søndergaard

Proceedings of the Proceedings Tenth and Eleventh International Workshop on Trends in Functional Programming In Education, 2022

Programming to Learn: Logic and Computation from a Programming Perspective.

Matthew Farrugia-Roberts, Bryn Jeffries, Harald Søndergaard

Proceedings of the ITiCSE 2022: Innovation and Technology in Computer Science Education, Dublin, Ireland, July 8, 2022