12 papers
Is the Last Layer Sufficient for Uncertainty Quantification?
Joseph Wilson, Chris van der Heide, Liam Hodgkinson +1
Epistemic uncertainty quantification (UQ) for deep neural networks (DNNs) is a requirement for safe adoption of AI in mission-critical settings. Several leading methods for UQ line…
The Geometric Wall: Manifold Structure Predicts Layerwise Sparse Autoencoder Scaling Laws
Eslam Zaher, Maciej Trzaskowski, Quan Nguyen +1
Sparse autoencoders (SAEs) operationalise the linear representation hypothesis: they reconstruct model activations as sparse linear combinations of interpretable dictionary atoms,…
Counterfactual Explanations on Robust Perceptual Geodesics
Eslam Zaher, Maciej Trzaskowski, Quan Nguyen +1
Latent-space optimization methods for counterfactual explanations - framed as minimal semantic perturbations that change model predictions - inherit the ambiguity of Wachter et al.…
The Interpolating Information Criterion for Overparameterized Models
Liam Hodgkinson, Chris van der Heide, Robert Salomone +2
The problem of model selection is considered for the setting of interpolating estimators, where the number of model parameters exceeds the size of the dataset. Classical informatio…
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…
Latent Refinement via Flow Matching for Training-free Linear Inverse Problem Solving
Hossein Askari, Yadan Luo, Hongfu Sun +1
Recent advances in inverse problem solving have increasingly adopted flow priors over diffusion models due to their ability to construct straight probability paths from noise to da…