mlsanityData to 7 Oct 2026

Stochastic approximation in non-markovian environments revisited

arXiv 2603.21091 ↗First posted 22 Mar 2026stat.ML cs.LG math.PRcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 3 of its 13 references that are in the map. First posted on arXiv 22 Mar 2026.

Builds on

3 of 13 references.

References · 3

  1. 2022Reinforcement Learning in Non-Markovian Environmentscited by 10
  2. 2026Training Dynamics of Softmax Self-Attention: Fast Global Convergence via Preconditioningcited by 4
  3. 2023Controlled Martingale Problems And Their Markov Mimicscited by 1

Built on by

Not cited yet.