Renormalization Group Guided Tensor Network Search
Analysis
This paper introduces RGTN, a novel framework for Tensor Network Structure Search (TN-SS) inspired by physics, specifically the Renormalization Group (RG). It addresses limitations in existing TN-SS methods by employing multi-scale optimization, continuous structure evolution, and efficient structure-parameter optimization. The core innovation lies in learnable edge gates and intelligent proposals based on physical quantities, leading to improved compression ratios and significant speedups compared to existing methods. The physics-inspired approach offers a promising direction for tackling the challenges of high-dimensional data representation.
Key Takeaways
- •Proposes RGTN, a novel framework for Tensor Network Structure Search (TN-SS).
- •Employs a physics-inspired approach using the Renormalization Group (RG).
- •Addresses limitations in existing TN-SS methods through multi-scale optimization and continuous structure evolution.
- •Achieves state-of-the-art compression ratios and significant speedups.
- •Uses learnable edge gates and intelligent proposals based on physical quantities.
“RGTN achieves state-of-the-art compression ratios and runs 4-600$\times$ faster than existing methods.”