Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.08169 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910907837186048 |
|---|---|
| author | Lev, Omri Wilson, Ashia C. |
| author_facet | Lev, Omri Wilson, Ashia C. |
| contents | Quantifying the influence of infinitesimal changes in training data on model performance is crucial for understanding and improving machine learning models. In this work, we reformulate this problem as a weighted empirical risk minimization and enhance existing influence function-based methods by using information geometry to derive a new algorithm to estimate influence. Our formulation proves versatile across various applications, and we further demonstrate in simulations how it remains informative even in non-convex cases. Furthermore, we show that our method offers significant computational advantages over current Newton step-based methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_08169 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | The Approximate Fisher Influence Function: Faster Estimation of Data Influence in Statistical Models Lev, Omri Wilson, Ashia C. Machine Learning Artificial Intelligence Quantifying the influence of infinitesimal changes in training data on model performance is crucial for understanding and improving machine learning models. In this work, we reformulate this problem as a weighted empirical risk minimization and enhance existing influence function-based methods by using information geometry to derive a new algorithm to estimate influence. Our formulation proves versatile across various applications, and we further demonstrate in simulations how it remains informative even in non-convex cases. Furthermore, we show that our method offers significant computational advantages over current Newton step-based methods. |
| title | The Approximate Fisher Influence Function: Faster Estimation of Data Influence in Statistical Models |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2407.08169 |