Robust Analysis for Resilient AI System
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918494302371840 |
|---|---|
| author | Wang, Yu Jin, Ran Kang, Lulu |
| author_facet | Wang, Yu Jin, Ran Kang, Lulu |
| contents | Operational hazards in Manufacturing Industrial Internet (MII) systems generate severe data outliers that cripple traditional statistical analysis. This paper proposes a novel robust regression method, DPD-Lasso, which integrates Density Power Divergence with Lasso regularization to analyze contaminated data from AI resilience experiments. We develop an efficient iterative algorithm to overcome previous computational bottlenecks. Applied to an MII testbed for Aerosol Jet Printing, DPD-Lasso provides reliable, stable performance on both clean and outlier-contaminated data, accurately quantifying hazard impacts. This work establishes robust regression as an essential tool for developing and validating resilient industrial AI systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_06172 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Robust Analysis for Resilient AI System Wang, Yu Jin, Ran Kang, Lulu Applications Machine Learning Operational hazards in Manufacturing Industrial Internet (MII) systems generate severe data outliers that cripple traditional statistical analysis. This paper proposes a novel robust regression method, DPD-Lasso, which integrates Density Power Divergence with Lasso regularization to analyze contaminated data from AI resilience experiments. We develop an efficient iterative algorithm to overcome previous computational bottlenecks. Applied to an MII testbed for Aerosol Jet Printing, DPD-Lasso provides reliable, stable performance on both clean and outlier-contaminated data, accurately quantifying hazard impacts. This work establishes robust regression as an essential tool for developing and validating resilient industrial AI systems. |
| title | Robust Analysis for Resilient AI System |
| topic | Applications Machine Learning |
| url | https://arxiv.org/abs/2509.06172 |