Stochastic approximation in non-markovian environments revisited
Machine Learning
2026-03-24 v1 Machine Learning
Probability
Abstract
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.
Cite
@article{arxiv.2603.21091,
title = {Stochastic approximation in non-markovian environments revisited},
author = {Vivek Shripad Borkar},
journal= {arXiv preprint arXiv:2603.21091},
year = {2026}
}