Lost in Retraining: Roaming the Parameter Space of Exponential Families Under Closed-Loop Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911046373998592 |
|---|---|
| author | Jangjoo, Fariba Marsili, Matteo Roudi, Yasser |
| author_facet | Jangjoo, Fariba Marsili, Matteo Roudi, Yasser |
| contents | Closed-loop learning is the process of repeatedly estimating a model from data generated from the model itself. It is receiving great attention due to the possibility that large neural network models may, in the future, be primarily trained with data generated by artificial neural networks themselves. We study this process for models that belong to exponential families, deriving equations of motions that govern the dynamics of the parameters. We show that maximum likelihood estimation of the parameters endows sufficient statistics with the martingale property and that as a result the process converges to absorbing states that amplify initial biases present in the data. However, we show that this outcome may be prevented if the data contains at least one data point generated from a ground truth model, by relying on maximum a posteriori estimation or by introducing regularisation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_20623 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Lost in Retraining: Roaming the Parameter Space of Exponential Families Under Closed-Loop Learning Jangjoo, Fariba Marsili, Matteo Roudi, Yasser Machine Learning Disordered Systems and Neural Networks Data Analysis, Statistics and Probability Closed-loop learning is the process of repeatedly estimating a model from data generated from the model itself. It is receiving great attention due to the possibility that large neural network models may, in the future, be primarily trained with data generated by artificial neural networks themselves. We study this process for models that belong to exponential families, deriving equations of motions that govern the dynamics of the parameters. We show that maximum likelihood estimation of the parameters endows sufficient statistics with the martingale property and that as a result the process converges to absorbing states that amplify initial biases present in the data. However, we show that this outcome may be prevented if the data contains at least one data point generated from a ground truth model, by relying on maximum a posteriori estimation or by introducing regularisation. |
| title | Lost in Retraining: Roaming the Parameter Space of Exponential Families Under Closed-Loop Learning |
| topic | Machine Learning Disordered Systems and Neural Networks Data Analysis, Statistics and Probability |
| url | https://arxiv.org/abs/2506.20623 |