A Unified Variational Design of Predictive Mirror Descent in Convex Games under Stochastic Feedback
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910279754842112 |
|---|---|
| author | Pan, Yunian Li, Tao Zhu, Quanyan |
| author_facet | Pan, Yunian Li, Tao Zhu, Quanyan |
| contents | Mirror descent provides a geometric framework for learning in games, but its last-iterate behavior can fail in weakly stable regimes, where the dynamics may exhibit rotational or recurrent transients. Predictive mirror methods mitigate this issue by modifying the feedback entering the mirror update, yet standard predictive variants are typically introduced algorithmically and analyzed one at a time. This letter gives a variational route to predictive feedback by constructing a stochastic mirror differential game with an auxiliary memory state. Its stage cost couples two Fenchel terms: a strategic term evaluated at a predicted profile and a corrective term driven by realized feedback. The resulting equilibrium feedback induces two-channel predictive mirror dynamics in general mirror geometry. Under local mirror regularity, a quantitative local Bregman growth condition, and bounded Brownian diffusion, we establish finite-horizon local terminal-time bounds in expectation and with high probability, together with an exit-probability estimate for the localization neighborhood. The result provides a unified variational construction of the induced predictive-memory mirror flow together with a local stochastic certificate for last-iterate performance near stable equilibria. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_01729 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Unified Variational Design of Predictive Mirror Descent in Convex Games under Stochastic Feedback Pan, Yunian Li, Tao Zhu, Quanyan Optimization and Control Computer Science and Game Theory Mirror descent provides a geometric framework for learning in games, but its last-iterate behavior can fail in weakly stable regimes, where the dynamics may exhibit rotational or recurrent transients. Predictive mirror methods mitigate this issue by modifying the feedback entering the mirror update, yet standard predictive variants are typically introduced algorithmically and analyzed one at a time. This letter gives a variational route to predictive feedback by constructing a stochastic mirror differential game with an auxiliary memory state. Its stage cost couples two Fenchel terms: a strategic term evaluated at a predicted profile and a corrective term driven by realized feedback. The resulting equilibrium feedback induces two-channel predictive mirror dynamics in general mirror geometry. Under local mirror regularity, a quantitative local Bregman growth condition, and bounded Brownian diffusion, we establish finite-horizon local terminal-time bounds in expectation and with high probability, together with an exit-probability estimate for the localization neighborhood. The result provides a unified variational construction of the induced predictive-memory mirror flow together with a local stochastic certificate for last-iterate performance near stable equilibria. |
| title | A Unified Variational Design of Predictive Mirror Descent in Convex Games under Stochastic Feedback |
| topic | Optimization and Control Computer Science and Game Theory |
| url | https://arxiv.org/abs/2606.01729 |