Liam Hodgkinson

activity

20242026

collaborators

3 papers

stat.ML2026

A Regularization-Sharpness Tradeoff for Linear Interpolators

Qingyi Hu, Liam Hodgkinson

The rule of thumb regarding the relationship between the bias-variance tradeoff and model size plays a key role in classical machine learning, but is now well-known to break down i…

stat.ML2025

Uncertainty Quantification with the Empirical Neural Tangent Kernel

Joseph Wilson, Chris van der Heide, Liam Hodgkinson +1

While neural networks have demonstrated impressive performance across various tasks, accurately quantifying uncertainty in their predictions is essential to ensure their trustworth…

math.DG2024

Computationally-assisted proof of a novel $O (3) \times O (10)$ -invariant Einstein metric on $S^{12}$

Timothy Buttsworth, Liam Hodgkinson

We prove existence of a non-round Einstein metric $g$ on $S^{12}$ that is invariant under the usual cohomogeneity one action of $O (3) \times O (10)$ on $S^{12}\subse…

A Regularization-Sharpness Tradeoff for Linear Interpolators

Uncertainty Quantification with the Empirical Neural Tangent Kernel

Computationally-assisted proof of a novel O(3)×O(10)-invariant Einstein metric on S12

Computationally-assisted proof of a novel $O (3) \times O (10)$ -invariant Einstein metric on $S^{12}$