Retrain or not retrain: Conformal test martingales for change-point detection

02/20/2021
by   Vladimir Vovk, et al.
0

We argue for supplementing the process of training a prediction algorithm by setting up a scheme for detecting the moment when the distribution of the data changes and the algorithm needs to be retrained. Our proposed schemes are based on exchangeability martingales, i.e., processes that are martingales under any exchangeable distribution for the data. Our method, based on conformal prediction, is general and can be applied on top of any modern prediction algorithm. Its validity is guaranteed, and in this paper we make first steps in exploring its efficiency.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

10/07/2020

Change point detection based on method of moment estimators

A change point detection procedure using the method of moment estimators...
04/18/2022

Usage of specific attention improves change point detection

The change point is a moment of an abrupt alteration in the data distrib...
04/03/2019

A new class of change point test statistics of Rényi type

A new class of change point test statistics is proposed that utilizes a ...
07/11/2019

Model based Level Shift Detection in Autocorrelated Data Streams using a moving window

Standard Control Chart techniques to detect level shift in data streams ...
05/15/2019

Robust change point tests by bounded transformations

Classical moment based change point tests like the cusum test are very p...
02/10/2021

Sequential change-point detection for mutually exciting point processes over networks

We present a new CUSUM procedure for sequentially detecting change-point...
01/16/2020

Cross-conformal e-prediction

This note discusses a simple modification of cross-conformal prediction ...
This week in AI

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