Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.06167 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908756764262400 |
|---|---|
| author | Rankawat, Anshum |
| author_facet | Rankawat, Anshum |
| contents | Parent-Guided Adaptive Reliability (PGAR) is a lightweight behavioural meta-learning framework that adds a supervisory "parent" layer on top of a standard learner to improve stability, calibration, and recovery under disturbances. PGAR computes three reflex-level signals (incident detection, overconfidence correction, and recovery memory) and fuses them into a bounded reliability index in [0,1]. This index continuously modulates the learner's effective learning rate, reducing update magnitude during instability and restoring it as reliability improves. We provide a Lyapunov-based proof sketch establishing bounded adaptation of the reliability dynamics under mild assumptions (smooth loss, descent direction, and bounded reflex outputs). Empirical evaluations on representative learning tasks show improved calibration, reduced loss variance, and faster recovery compared to standard optimizers, while retaining computational simplicity. PGAR functions as a plug-in reliability layer for existing optimization and learning pipelines, supporting interpretable reliability traces in safety-relevant settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_06167 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Parent-Guided Adaptive Reliability (PGAR): A Behavioural Meta-Learning Framework for Stable and Trustworthy AI Rankawat, Anshum Machine Learning Artificial Intelligence Parent-Guided Adaptive Reliability (PGAR) is a lightweight behavioural meta-learning framework that adds a supervisory "parent" layer on top of a standard learner to improve stability, calibration, and recovery under disturbances. PGAR computes three reflex-level signals (incident detection, overconfidence correction, and recovery memory) and fuses them into a bounded reliability index in [0,1]. This index continuously modulates the learner's effective learning rate, reducing update magnitude during instability and restoring it as reliability improves. We provide a Lyapunov-based proof sketch establishing bounded adaptation of the reliability dynamics under mild assumptions (smooth loss, descent direction, and bounded reflex outputs). Empirical evaluations on representative learning tasks show improved calibration, reduced loss variance, and faster recovery compared to standard optimizers, while retaining computational simplicity. PGAR functions as a plug-in reliability layer for existing optimization and learning pipelines, supporting interpretable reliability traces in safety-relevant settings. |
| title | Parent-Guided Adaptive Reliability (PGAR): A Behavioural Meta-Learning Framework for Stable and Trustworthy AI |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2601.06167 |