Expander Graphs
Cross-source consensus on Expander Graphs from 1 sources and 5 claims.
1 sources · 5 claims
Uses
How it works
Evidence quality
Highlighted claims
- Random d-regular expander graphs are used as fixed near-linear sparse proxies. — Graph-SND: Sparse Aggregation for Behavioral Diversity in Multi-Agent Reinforcement Learning
- For d-regular spectral expanders, d equal to Theta(log n) yields O(log n) worst-case relative distortion with Theta(n log n) edges. — Graph-SND: Sparse Aggregation for Behavioral Diversity in Multi-Agent Reinforcement Learning
- Expander experiments produced d-regular ratios very close to one across tested n and d values. — Graph-SND: Sparse Aggregation for Behavioral Diversity in Multi-Agent Reinforcement Learning
- The spectral nuclear-norm refinement suggests low-effective-rank MARL distance matrices can be easier than worst-case metric tables. — Graph-SND: Sparse Aggregation for Behavioral Diversity in Multi-Agent Reinforcement Learning
- The article says theory does not fully explain the near-unit empirical expander ratios. — Graph-SND: Sparse Aggregation for Behavioral Diversity in Multi-Agent Reinforcement Learning