Statistical inference on black-box generative models in the data kernel perspective space

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Helm, Hayden, Acharyya, Aranyak, Duderstadt, Brandon, Park, Youngser, Priebe, Carey E.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916752151019520
author Helm, Hayden
Acharyya, Aranyak
Duderstadt, Brandon
Park, Youngser
Priebe, Carey E.
author_facet Helm, Hayden
Acharyya, Aranyak
Duderstadt, Brandon
Park, Youngser
Priebe, Carey E.
contents Generative models are capable of producing human-expert level content across a variety of topics and domains. As the impact of generative models grows, it is necessary to develop statistical methods to understand collections of available models. These methods are particularly important in settings where the user may not have access to information related to a model's pre-training data, weights, or other relevant model-level covariates. In this paper we extend recent results on representations of black-box generative models to model-level statistical inference tasks. We demonstrate that the model-level representations are effective for multiple inference tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2410_01106
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Statistical inference on black-box generative models in the data kernel perspective space
Helm, Hayden
Acharyya, Aranyak
Duderstadt, Brandon
Park, Youngser
Priebe, Carey E.
Machine Learning
Generative models are capable of producing human-expert level content across a variety of topics and domains. As the impact of generative models grows, it is necessary to develop statistical methods to understand collections of available models. These methods are particularly important in settings where the user may not have access to information related to a model's pre-training data, weights, or other relevant model-level covariates. In this paper we extend recent results on representations of black-box generative models to model-level statistical inference tasks. We demonstrate that the model-level representations are effective for multiple inference tasks.
title Statistical inference on black-box generative models in the data kernel perspective space
topic Machine Learning
url https://arxiv.org/abs/2410.01106