most citedPlex: Towards Reliability using Pretrained Large Model Extensions

38 citations · 42 across the 3 of their papers we have counts for

collaborators

6 papers

cs.LG20237 cited

Prediction-Oriented Bayesian Active Learning

Freddie Bickford Smith, Andreas Kirsch, Sebastian Farquhar +3

Information-theoretic approaches to active learning have traditionally focused on maximising the information gathered about the model parameters, most commonly by optimising the BA…

cs.LG2023

Does "Deep Learning on a Data Diet" reproduce? Overall yes, but GraNd at Initialization does not

Andreas Kirsch

The paper 'Deep Learning on a Data Diet' by Paul et al. (2021) introduces two innovative metrics for pruning datasets during the training of neural networks. While we are able to r…

cs.LG20231 cited

Speeding Up BatchBALD: A k-BALD Family of Approximations for Active Learning

Andreas Kirsch

Active learning is a powerful method for training machine learning models with limited labeled data. One commonly used technique for active learning is BatchBALD, which uses Bayesi…

cs.LG20223 cited

Unifying Approaches in Active Learning and Active Sampling via Fisher Information and Information-Theoretic Quantities

Andreas Kirsch, Yarin Gal

Recently proposed methods in data subset selection, that is active learning and active sampling, use Fisher information, Hessians, similarity matrices based on gradients, and gradi…

cs.LG202238 cited

Plex: Towards Reliability using Pretrained Large Model Extensions

Dustin Tran, Jeremiah Liu, Michael W. Dusenberry +23

A recent trend in artificial intelligence is the use of pretrained models for language and vision tasks, which have achieved extraordinary performance but also puzzling failures. P…

math.AP20221 cited

Corrigendum to "Inverse Problems for abstract evolution equations II: higher order differentiability for viscoelasticity

Andreas Kirsch, Andreas Rieder

In our paper [SIAM J.\ Appl.~Math.\ 79-6 (2019), https://doi.org/10.1137/19M1269403] we considered full waveform inversion (FWI) in the viscoelastic regime. FWI entails the nonline…