Salvato in:
Dettagli Bibliografici
Autori principali: Aliakbarpour, Maryam, Bairaktari, Konstantina, Smith, Adam, Swanberg, Marika, Ullman, Jonathan
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2412.12374
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913615254126592
author Aliakbarpour, Maryam
Bairaktari, Konstantina
Smith, Adam
Swanberg, Marika
Ullman, Jonathan
author_facet Aliakbarpour, Maryam
Bairaktari, Konstantina
Smith, Adam
Swanberg, Marika
Ullman, Jonathan
contents Model personalization allows a set of individuals, each facing a different learning task, to train models that are more accurate for each person than those they could develop individually. The goals of personalization are captured in a variety of formal frameworks, such as multitask learning and metalearning. Combining data for model personalization poses risks for privacy because the output of an individual's model can depend on the data of other individuals. In this work we undertake a systematic study of differentially private personalized learning. Our first main contribution is to construct a taxonomy of formal frameworks for private personalized learning. This taxonomy captures different formal frameworks for learning as well as different threat models for the attacker. Our second main contribution is to prove separations between the personalized learning problems corresponding to different choices. In particular, we prove a novel separation between private multitask learning and private metalearning.
format Preprint
id arxiv_https___arxiv_org_abs_2412_12374
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Privacy in Metalearning and Multitask Learning: Modeling and Separations
Aliakbarpour, Maryam
Bairaktari, Konstantina
Smith, Adam
Swanberg, Marika
Ullman, Jonathan
Machine Learning
Cryptography and Security
Model personalization allows a set of individuals, each facing a different learning task, to train models that are more accurate for each person than those they could develop individually. The goals of personalization are captured in a variety of formal frameworks, such as multitask learning and metalearning. Combining data for model personalization poses risks for privacy because the output of an individual's model can depend on the data of other individuals. In this work we undertake a systematic study of differentially private personalized learning. Our first main contribution is to construct a taxonomy of formal frameworks for private personalized learning. This taxonomy captures different formal frameworks for learning as well as different threat models for the attacker. Our second main contribution is to prove separations between the personalized learning problems corresponding to different choices. In particular, we prove a novel separation between private multitask learning and private metalearning.
title Privacy in Metalearning and Multitask Learning: Modeling and Separations
topic Machine Learning
Cryptography and Security
url https://arxiv.org/abs/2412.12374