Buchholz, Oliver (2023) The Deep Neural Network Approach to the Reference Class Problem. [Preprint]

Preview

Text RCP_preprint.pdf Download (467kB) | Preview

Abstract

Methods of machine learning (ML) are gradually complementing and sometimes even replacing methods of classical statistics in science. This raises the question whether ML faces the same methodological problems as classical statistics. This paper sheds light on this question by investigating a long-standing challenge to classical statistics: the reference class problem (RCP). It arises whenever statistical evidence is applied to an individual object, since the individual belongs to several reference classes and evidence might vary across them. Thus, the problem consists in choosing a suitable reference class for the individual. I argue that deep neural networks (DNNs) are able to overcome specific instantiations of the RCP. Whereas the criteria of narrowness, reliability, and homogeneity, that have been proposed to determine a suitable reference class, pose an inextricable tradeoff to classical statistics, DNNs are able to satisfy them in some situations. On the one hand, they can exploit the high dimensionality in big-data settings. I argue that this corresponds to the criteria of narrowness and reliability. On the other hand, ML research indicates that DNNs are generally not susceptible to overfitting. I argue that this property is related to a particular form of homogeneity. Taking both aspects together reveals that there are specific settings in which DNNs can overcome the RCP.

---

Export/Citation:

EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL

Social Networking:

Share |

---

Item Type:	Preprint
Creators:	Creators Email ORCID Buchholz, Oliver oliver.buchholz@uni-tuebingen.de 0000-0002-4905-753X
Keywords:	reference class problem, prediction, overfitting, machine learning, deep neural networks, big data
Subjects:	General Issues > Data Specific Sciences > Artificial Intelligence > Machine Learning Specific Sciences > Probability/Statistics General Issues > Technology
Depositing User:	Mr. Oliver Buchholz
Date Deposited:	20 Feb 2023 14:28
Last Modified:	20 Feb 2023 14:28
Item ID:	21777
Subjects:	General Issues > Data Specific Sciences > Artificial Intelligence > Machine Learning Specific Sciences > Probability/Statistics General Issues > Technology
Date:	February 2023
URI:	https://philsci-archive.pitt.edu/id/eprint/21777

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item