Riemannian Manifold Learning for Stackelberg Games with Neural Flow Representations
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909904486268928 |
|---|---|
| author | Liu, Larkin Rasul, Kashif Chao, Yutong Etesami, Jalal |
| author_facet | Liu, Larkin Rasul, Kashif Chao, Yutong Etesami, Jalal |
| contents | We present a novel framework for online learning in Stackelberg general-sum games, where two agents, the leader and follower, engage in sequential turn-based interactions. At the core of this approach is a learned diffeomorphism that maps the joint action space to a smooth spherical Riemannian manifold, referred to as the Stackelberg manifold. This mapping, facilitated by neural normalizing flows, ensures the formation of tractable isoplanar subspaces, enabling efficient techniques for online learning. Leveraging the linearity of the agents' reward functions on the Stackelberg manifold, our construct allows the application of linear bandit algorithms. We then provide a rigorous theoretical basis for regret minimization on the learned manifold and establish bounds on the simple regret for learning Stackelberg equilibrium. This integration of manifold learning into game theory uncovers a previously unrecognized potential for neural normalizing flows as an effective tool for multi-agent learning. We present empirical results demonstrating the effectiveness of our approach compared to standard baselines, with applications spanning domains such as cybersecurity and economic supply chain optimization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_05498 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Riemannian Manifold Learning for Stackelberg Games with Neural Flow Representations Liu, Larkin Rasul, Kashif Chao, Yutong Etesami, Jalal Machine Learning Artificial Intelligence Computer Science and Game Theory Multiagent Systems 91A10 I.2.6; I.2.11 We present a novel framework for online learning in Stackelberg general-sum games, where two agents, the leader and follower, engage in sequential turn-based interactions. At the core of this approach is a learned diffeomorphism that maps the joint action space to a smooth spherical Riemannian manifold, referred to as the Stackelberg manifold. This mapping, facilitated by neural normalizing flows, ensures the formation of tractable isoplanar subspaces, enabling efficient techniques for online learning. Leveraging the linearity of the agents' reward functions on the Stackelberg manifold, our construct allows the application of linear bandit algorithms. We then provide a rigorous theoretical basis for regret minimization on the learned manifold and establish bounds on the simple regret for learning Stackelberg equilibrium. This integration of manifold learning into game theory uncovers a previously unrecognized potential for neural normalizing flows as an effective tool for multi-agent learning. We present empirical results demonstrating the effectiveness of our approach compared to standard baselines, with applications spanning domains such as cybersecurity and economic supply chain optimization. |
| title | Riemannian Manifold Learning for Stackelberg Games with Neural Flow Representations |
| topic | Machine Learning Artificial Intelligence Computer Science and Game Theory Multiagent Systems 91A10 I.2.6; I.2.11 |
| url | https://arxiv.org/abs/2502.05498 |