Performative Prediction in a Stateful World

11/08/2020
by   Gavin Brown, et al.
14

Deployed supervised machine learning models make predictions that interact with and influence the world. This phenomenon is called "performative prediction" by Perdomo et al. (2020), who investigated it in a stateless setting. We generalize their results to the case where the response of the population to the deployed classifier depends both on the classifier and the previous distribution of the population. We also demonstrate such a setting empirically, for the scenario of strategic manipulation.

READ FULL TEXT

Authors

page 1

page 2

page 3

page 4

12/13/2021

How to Learn when Data Gradually Reacts to Your Model

A recent line of work has focused on training machine learning (ML) mode...
02/23/2021

Strategic Classification in the Dark

Strategic classification studies the interaction between a classificatio...
06/14/2021

Inference with generalizable classifier predictions

This paper addresses the problem of making statistical inference about a...
02/16/2020

Performative Prediction

When predictions support decisions they may influence the outcome they a...
06/17/2022

Strategic Representation

Humans have come to rely on machines for reducing excessive information ...
10/02/2017

The Strategy of Experts for Repeated Predictions

We investigate the behavior of experts who seek to make predictions with...
08/04/2020

The Strategic Perceptron

The classical Perceptron algorithm provides a simple and elegant procedu...

Code Repositories

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.