The Limitations of Model Retraining in the Face of Performativity
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909288880930816 |
|---|---|
| author | Kabra, Anmol Patel, Kumar Kshitij |
| author_facet | Kabra, Anmol Patel, Kumar Kshitij |
| contents | We study stochastic optimization in the context of performative shifts, where the data distribution changes in response to the deployed model. We demonstrate that naive retraining can be provably suboptimal even for simple distribution shifts. The issue worsens when models are retrained given a finite number of samples at each retraining step. We show that adding regularization to retraining corrects both of these issues, attaining provably optimal models in the face of distribution shifts. Our work advocates rethinking how machine learning models are retrained in the presence of performative effects. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_08499 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | The Limitations of Model Retraining in the Face of Performativity Kabra, Anmol Patel, Kumar Kshitij Machine Learning Computer Science and Game Theory We study stochastic optimization in the context of performative shifts, where the data distribution changes in response to the deployed model. We demonstrate that naive retraining can be provably suboptimal even for simple distribution shifts. The issue worsens when models are retrained given a finite number of samples at each retraining step. We show that adding regularization to retraining corrects both of these issues, attaining provably optimal models in the face of distribution shifts. Our work advocates rethinking how machine learning models are retrained in the presence of performative effects. |
| title | The Limitations of Model Retraining in the Face of Performativity |
| topic | Machine Learning Computer Science and Game Theory |
| url | https://arxiv.org/abs/2408.08499 |