Optimal Classification under Performative Distribution Shift

Cyffers, Edwige; Pydi, Muni Sreenivas; Atif, Jamal; Cappé, Olivier

Document type :

Autre communication scientifique (congrès sans actes - poster - séminaire...): Communication dans un congrès avec actes

Permalink :

http://hdl.handle.net/20.500.12210/118346

Title :

Optimal Classification under Performative Distribution Shift

Author(s) :

Cyffers, Edwige [Auteur]
Université de Lille
Machine Learning in Information Networks [MAGNET]
Pydi, Muni Sreenivas [Auteur]
Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]
Machine Intelligence and Learning Systems [MILES]
Atif, Jamal [Auteur]
Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]
Cappé, Olivier [Auteur]
Département d'informatique - ENS Paris [DI-ENS]

Conference title :

38th Conference on Neural Information Processing Systems

City :

Vancouver (Canada)

Country :

Canada

Start date of the conference :

2024-12-10

HAL domain(s) :

Informatique [cs]/Apprentissage [cs.LG]

English abstract : [en]

<div><p>Performative learning addresses the increasingly pervasive situations in which algorithmic decisions may induce changes in the data distribution as a consequence of their public deployment. We propose a novel view ...
Show more ><div><p>Performative learning addresses the increasingly pervasive situations in which algorithmic decisions may induce changes in the data distribution as a consequence of their public deployment. We propose a novel view in which these performative effects are modelled as push-forward measures. This general framework encompasses existing models and enables novel performative gradient estimation methods, leading to more efficient and scalable learning strategies. For distribution shifts, unlike previous models which require full specification of the data distribution, we only assume knowledge of the shift operator that represents the performative changes. This approach can also be integrated into various change-of-variablebased models, such as VAEs or normalizing flows. Focusing on classification with a linear-in-parameters performative effect, we prove the convexity of the performative risk under a new set of assumptions. Notably, we do not limit the strength of performative effects but rather their direction, requiring only that classification becomes harder when deploying more accurate models. In this case, we also establish a connection with adversarially robust classification by reformulating the minimization of the performative risk as a min-max variational problem. Finally, we illustrate our approach on synthetic and real datasets.</p></div>Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

ANR Project :

Programme de formation doctorale en IA à Lille
Secure, safe and fair machine learning for healthcare

Collections :

Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL

Submission date :

2024-11-05T03:05:43Z

Files

document
Open access
Access the document

paper.pdf
Open access
Access the document

Optimal Classification under Performative ... BibTeX CSV Excel RIS

Files

Optimal Classification under Performative ...

BibTeX

CSV

Excel

RIS