Stochastic approximation in non-markovian environments revisited
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915880945844224 |
|---|---|
| author | Borkar, Vivek Shripad |
| author_facet | Borkar, Vivek Shripad |
| contents | Based on some recent work of the author on stochastic approximation in non-markovian environments, the situation when the driving random process is non-ergodic in addition to being non-markovian is considered. Using this, we propose an analytic framework for understanding transformer based learning, specifically, the `attention' mechanism, and continual learning, both of which depend on the entire past in principle. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_21091 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Stochastic approximation in non-markovian environments revisited Borkar, Vivek Shripad Machine Learning Probability 62L20 Based on some recent work of the author on stochastic approximation in non-markovian environments, the situation when the driving random process is non-ergodic in addition to being non-markovian is considered. Using this, we propose an analytic framework for understanding transformer based learning, specifically, the `attention' mechanism, and continual learning, both of which depend on the entire past in principle. |
| title | Stochastic approximation in non-markovian environments revisited |
| topic | Machine Learning Probability 62L20 |
| url | https://arxiv.org/abs/2603.21091 |