Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Acevedo, Nicolas, Cortez, Carmen, Brooks, Chris, Kizilcec, Rene, Yu, Renzhe
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2405.14186
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916257516748800
author Acevedo, Nicolas
Cortez, Carmen
Brooks, Chris
Kizilcec, Rene
Yu, Renzhe
author_facet Acevedo, Nicolas
Cortez, Carmen
Brooks, Chris
Kizilcec, Rene
Yu, Renzhe
contents Distribution shift is a common situation in machine learning tasks, where the data used for training a model is different from the data the model is applied to in the real world. This issue arises across multiple technical settings: from standard prediction tasks, to time-series forecasting, and to more recent applications of large language models (LLMs). This mismatch can lead to performance reductions, and can be related to a multiplicity of factors: sampling issues and non-representative data, changes in the environment or policies, or the emergence of previously unseen scenarios. This brief focuses on the definition and detection of distribution shifts in educational settings. We focus on standard prediction problems, where the task is to learn a model that takes in a series of input (predictors) $X=(x_1,x_2,...,x_m)$ and produces an output $Y=f(X)$.
format Preprint
id arxiv_https___arxiv_org_abs_2405_14186
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Fairness Hub Technical Briefs: Definition and Detection of Distribution Shift
Acevedo, Nicolas
Cortez, Carmen
Brooks, Chris
Kizilcec, Rene
Yu, Renzhe
Machine Learning
Computers and Society
Distribution shift is a common situation in machine learning tasks, where the data used for training a model is different from the data the model is applied to in the real world. This issue arises across multiple technical settings: from standard prediction tasks, to time-series forecasting, and to more recent applications of large language models (LLMs). This mismatch can lead to performance reductions, and can be related to a multiplicity of factors: sampling issues and non-representative data, changes in the environment or policies, or the emergence of previously unseen scenarios. This brief focuses on the definition and detection of distribution shifts in educational settings. We focus on standard prediction problems, where the task is to learn a model that takes in a series of input (predictors) $X=(x_1,x_2,...,x_m)$ and produces an output $Y=f(X)$.
title Fairness Hub Technical Briefs: Definition and Detection of Distribution Shift
topic Machine Learning
Computers and Society
url https://arxiv.org/abs/2405.14186