44 citations · 68 across the 8 of their papers we have counts for
9 papers
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…
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…
Computationally-assisted proof of a novel -invariant Einstein metric on
Timothy Buttsworth, Liam Hodgkinson
We prove existence of a non-round Einstein metric on that is invariant under the usual cohomogeneity one action of on $S^{12}\subse…
Noisy Recurrent Neural Networks
Soon Hoe Lim, N. Benjamin Erichson, Liam Hodgkinson +1
We provide a general framework for studying recurrent neural networks (RNNs) trained by injecting noise into hidden states. Specifically, we consider RNNs that can be viewed as dis…
Stochastic Normalizing Flows
Liam Hodgkinson, Chris van der Heide, Fred Roosta +1
We introduce stochastic normalizing flows, an extension of continuous normalizing flows for maximum likelihood estimation and variational inference (VI) using stochastic differenti…
The reproducing Stein kernel approach for post-hoc corrected sampling
Liam Hodgkinson, Robert Salomone, Fred Roosta
Stein importance sampling is a widely applicable technique based on kernelized Stein discrepancy, which corrects the output of approximate sampling algorithms by reweighting the em…