SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2011.03885 · NeurIPS · 2020

Performative Prediction in a Stateful World

Gavin Brown, Shlomi Hod, Iden Kalemaj

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Deployed supervised machine learning models make predictions that interact with and influence the world. This phenomenon is called performative prediction by Perdomo et al. (ICML 2020). It is an ongoing challenge to understand the influence of such predictions as well as design tools so as to control that influence. We propose a theoretical framework where the response of a target population to the deployed classifier is modeled as a function of the classifier and the current state (distribution) of the population. We show necessary and sufficient conditions for convergence to an equilibrium of two retraining algorithms, repeated risk minimization and a lazier variant. Furthermore, convergence is near an optimal classifier. We thus generalize results of Perdomo et al., whose performativity framework does not assume any dependence on the state of the target population. A particular phenomenon captured by our model is that of distinct groups that acquire information and resources at different rates to be able to respond to the latest deployed classifier. We study this phenomenon theoretically and empirically. Definition 1 (ε-joint sensitivity). The transition map Tr(; ) is ε-jointly sensitive if, for all θ, θ ∈ Θ and d, d ∈ ∆(Z), W 1 (Tr(d; θ), Tr(d ; θ )) ≤ εW 1 (d, d ) + ε θ -θ 2 , where W 1 denotes the Wasserstein-1 distance between distributions.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2011.03885")
get_code_for_paper("2011.03885")
have("2011.03885")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2011.03885.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2011.03885.svg)](https://syntology.ai/paper/2011.03885)

Connect an agent — have() is free.