5 citations · 16 across the 5 of their papers we have counts for
5 papers
Theoretical and Practical Perspectives on what Influence Functions Do
Andrea Schioppa, Katja Filippova, Ivan Titov +1
Influence functions (IF) have been seen as a technique for explaining model predictions through the lens of the training data. Their utility is assumed to be in identifying trainin…
Cross-Lingual Supervision improves Large Language Models Pre-training
Andrea Schioppa, Xavier Garcia, Orhan Firat
The recent rapid progress in pre-training Large Language Models has relied on using self-supervised language modeling objectives like next token prediction or span corruption. On t…
An example of a differentiability space which is PI-unrectifiable
Andrea Schioppa
We construct a (Lipschitz) differentiability space which has at generic points a disconnected tangent and thus does not contain positive measure subsets isometric to positive measu…
Unrectifiable normal currents in Euclidean spaces
Andrea Schioppa
We construct in a -dimensional simple normal current whose support is purely -unrectifiable. The result is sharp because the support of a normal current ca…
On the relationship between derivations and measurable differentiable structures on metric measure spaces
Andrea Schioppa
We investigate the relationship between measurable differentiable structures on doubling metric measure spaces and derivations. We prove: [1] a decomposition theorem for the module…