WANDER: An Explainable Decision-Support Framework for HPC
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911338137124864 |
|---|---|
| author | Lahiry, Ankur Banday, Banooqa Bhattarai, Yugesh Islam, Tanzima Z. |
| author_facet | Lahiry, Ankur Banday, Banooqa Bhattarai, Yugesh Islam, Tanzima Z. |
| contents | High-performance computing (HPC) systems expose many interdependent configuration knobs that impact runtime, resource usage, power, and variability. Existing predictive tools model these outcomes, but do not support structured exploration, explanation, or guided reconfiguration. We present WANDER, a decision-support framework that synthesizes alternate configurations using counterfactual analysis aligned with user goals and constraints. We introduce a composite trade-off score that ranks suggestions based on prediction uncertainty, consistency between feature-target relationships using causal models, and similarity between feature distributions against historical data. To our knowledge, WANDER is the first such system to unify prediction, exploration, and explanation for HPC tuning under a common query interface. Across multiple datasets WANDER generates interpretable and trustworthy, human-readable alternatives that guide users to achieve their performance objectives. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_04049 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | WANDER: An Explainable Decision-Support Framework for HPC Lahiry, Ankur Banday, Banooqa Bhattarai, Yugesh Islam, Tanzima Z. Performance Artificial Intelligence High-performance computing (HPC) systems expose many interdependent configuration knobs that impact runtime, resource usage, power, and variability. Existing predictive tools model these outcomes, but do not support structured exploration, explanation, or guided reconfiguration. We present WANDER, a decision-support framework that synthesizes alternate configurations using counterfactual analysis aligned with user goals and constraints. We introduce a composite trade-off score that ranks suggestions based on prediction uncertainty, consistency between feature-target relationships using causal models, and similarity between feature distributions against historical data. To our knowledge, WANDER is the first such system to unify prediction, exploration, and explanation for HPC tuning under a common query interface. Across multiple datasets WANDER generates interpretable and trustworthy, human-readable alternatives that guide users to achieve their performance objectives. |
| title | WANDER: An Explainable Decision-Support Framework for HPC |
| topic | Performance Artificial Intelligence |
| url | https://arxiv.org/abs/2506.04049 |