Research map / Architectures and efficiency / RNNs and normalization
Renormalization Group Guided Tensor Network Structure Search
Maolin Wang, Bowen Yu, Sheng Zhang, Linjie Mi, Wanyu Wang, Yiqi Wang, Pengyue Jia, Xuetao Wei, Zenglin Xu, Ruocheng Guo, Xiangyu Zhao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use RGTN instead of SVDinsTN | SVDinsTN · Light field Bunny, RE 0.01 | compression ratio: 22.6% -> 22.3% | Improved |
| use RGTN instead of SVDinsTN | SVDinsTN · Light field Knights, RE 0.01 | compression ratio: 31.7% -> 29.9% | Improved |
| use RGTN instead of SVDinsTN | SVDinsTN · Light field Bunny, RE 0.1 | compression ratio: 2.69% -> 0.91% | Improved |
| use RGTN instead of SVDinsTN | SVDinsTN · Light field Bunny, RE 0.01 | run time: 0.752 -> 0.180 (x1000s) | Improved |
| use RGTN instead of TNGA/TNLS | TNLS · Light field, RE 0.01 | run time: 1388 -> 0.180 (x1000s, Bunny) | Improved |
| use RGTN instead of SVDinsTN | SVDinsTN · 8th-order synthetic tensor, RE 0.01 | compression ratio: 0.016% -> 0.009% | Improved |
| use RGTN instead of SVDinsTN | SVDinsTN · 8th-order synthetic tensor, RE 0.01 | run time: 0.017 -> 0.123 (x1000s) | Hurt |
| use RGTN instead of SVDinsTN | SVDinsTN · Video completion News | MPSNR: 31.643 -> 32.040 | Improved |
| use RGTN instead of SVDinsTN | SVDinsTN · Video completion Silent | MPSNR: 32.706 -> 30.620 | Hurt |
| use RGTN instead of SVDinsTN | SVDinsTN · Video completion News | time: 932.42 -> 135.95 seconds | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SVDinsTN — SVDinsTN: A Tensor Network Paradigm for Efficient Structure Search from Regularized Modeling Perspective (CVPR 2024) · better on 8 of 9 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- tnGPS: Discovering Unknown Tensor Network Structure Search Algorithms via Large Language Models (LLMs) (ICML 2024 · similarity 0.88)
- SVDinsTN: A Tensor Network Paradigm for Efficient Structure Search from Regularized Modeling Perspective (CVPR 2024 · similarity 0.88)
- A Space Group Symmetry Informed Network for O(3) Equivariant Crystal Tensor Prediction (ICML 2024 · similarity 0.86)
- A Renormalization Group Framework for Scale-Invariant Feature Learning in Deep Neural Networks (Student Abstract) (AAAI 2025 · similarity 0.85)
- Riemann Tensor Neural Networks: Learning Conservative Systems with Physics-Constrained Networks (ICML 2025 · similarity 0.84)
- Geometry-aware training of factorized layers in tensor Tucker format (NeurIPS 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
