Dear all /Bonjour à tous,

We are happy to invite you to the Predoc III evaluation of Pedram Khorsandi on December 17th at 12h30 pm (hybrid mode).

Vous êtes cordialement invité.e.s à l'évaluation du Predoc III de Pedram Khorsandi, le 17 décembre à 12h30 (mode hybride).

Jury

Abstract

Performative Prediction is a framework accounting for the shift in the data
distribution induced by the prediction of a model deployed in the real
world. Ensuring rapid convergence to a stable solution where the data
distribution remains the same after the model deployment is crucial,
especially in evolving environments. We extend the Repeated Risk
Minimization (RRM) framework by utilizing historical datasets from previous
retraining snapshots, yielding a class of algorithms that we call Affine
Risk Minimizers and enabling convergence to a performatively stable point
for a broader class of problems. We introduce a new upper bound for methods
that use only the final iteration of the dataset and prove for the first
time the tightness of both this new bound and the previous existing bounds
within the same regime. We also prove that utilizing historical datasets
can surpass the lower bound for last iterate RRM, and empirically observe
faster convergence to the stable point on various performative prediction
benchmarks. We offer at the same time the first lower bound analysis for
RRM within the class of Affine Risk Minimizers, quantifying the potential
improvements in convergence speed that could be achieved with other
variants in our framework.