4 papers · 1 filter
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…
Distributed Function Minimization in Apache Spark
Andrea Schioppa
We report on an open-source implementation for distributed function minimization on top of Apache Spark by using gradient and quasi-Newton methods. We show-case it with an applicat…
Learning to Transport with Neural Networks
Andrea Schioppa
We compare several approaches to learn an Optimal Map, represented as a neural network, between probability distributions. The approaches fall into two categories: ``Heuristics'' a…
Optimality of the final model found via Stochastic Gradient Descent
Andrea Schioppa
We study convergence properties of Stochastic Gradient Descent (SGD) for convex objectives without assumptions on smoothness or strict convexity. We consider the question of establ…