activity
20192026
most citedMultiplicative noise and heavy tails in stochastic optimization

32 citations · 43 across the 16 of their papers we have counts for

collaborators
Showing 2023 · stat.MLShow all

5 papers · 2 filters

stat.ML2023

A PAC-Bayesian Perspective on the Interpolating Information Criterion

Liam Hodgkinson, Chris van der Heide, Robert Salomone +2

Deep learning is renowned for its theory-practice gap, whereby principled theory typically fails to provide much beneficial guidance for implementation in practice. This has been h…

stat.ML2023

Generalization Guarantees via Algorithm-dependent Rademacher Complexity

Sarah Sachs, Tim van Erven, Liam Hodgkinson +2

Algorithm- and data-dependent generalization bounds are required to explain the generalization behavior of modern machine learning algorithms. In this context, there exists informa…

stat.ML2023★ 2 cited

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…

stat.ML2023

A Heavy-Tailed Algebra for Probabilistic Programming

Feynman Liang, Liam Hodgkinson, Michael W. Mahoney

Despite the successes of probabilistic models based on passing noise through neural networks, recent work has identified that such methods often fail to capture tail behavior accur…

stat.ML2023★ 4 cited

When are ensembles really effective?

Ryan Theisen, Hyunsuk Kim, Yaoqing Yang +2

Ensembling has a long history in statistical data analysis, with many impactful applications. However, in many modern machine learning settings, the benefits of ensembling are less…