Research map / Learning theory and algorithms / Matrix and tensor methods
Machine Learning With Tree Tensor Networks, CP Rank Constraints, and Tensor Dropout
Hao Chen, Thomas Barthel
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 |
|---|---|---|---|
| add CP rank constraint (low-rank tensors) to the TTN classifier (ablation) | TTN classifier, b=4 · MNIST | accuracy (%): 92-93% validation (full TTN, m>4) -> 98.3% test | Improved |
| add CP rank constraint (low-rank tensors) to the TTN classifier (ablation) | TTN classifier, b=4 · Fashion-MNIST | accuracy (%): 84% validation (full TTN) -> 88.5% test | Improved |
| add tensor dropout (p=0.2) to low-rank TTN (ablation) | low-rank TTN, b=4 · Fashion-MNIST | validation accuracy: improved by about 1-2% | Improved |
| add tensor dropout to low-rank TTN (best at m=16, r=64, p=0.3) (ablation) | low-rank TTN, b=4 · Fashion-MNIST test | accuracy (%): 88.5% -> 90.3% | Improved |
| increase branching ratio from 2 to 4 (ablation) | low-rank TTN · Fashion-MNIST test | accuracy (%): b=2 generally lower by around 4% | Improved |
| increase bond dimension m in full TTN (ablation) | full TTN, b=4 · MNIST | validation accuracy: m > 4 all give approximately 92-93% | No clear effect |
| increase CP rank r beyond bond dimension m (ablation) | low-rank TTN · MNIST and Fashion-MNIST | accuracy | No clear effect |
| increase tensor dropout rate beyond critical p_c (ablation) | low-rank TTN, b=4, m=16 · Fashion-MNIST test | accuracy | Mixed |
| low-rank TTN with dropout versus AlexNet | low-rank TTN · Fashion-MNIST test | accuracy (%): 89.9% -> 90.3% | Improved |
| low-rank TTN with dropout versus GoogLeNet | low-rank TTN · Fashion-MNIST test | accuracy (%): 93.7% vs 90.3% | Hurt |
Closest papers by meaning
- Deep Tree Tensor Networks (NeurIPS 2025 · similarity 0.91)
- Supervised Learning with Tensor Networks (NeurIPS 2016 · similarity 0.89)
- Efficient Leverage Score Sampling for Tensor Train Decomposition (NeurIPS 2024 · similarity 0.86)
- Riemann Tensor Neural Networks: Learning Conservative Systems with Physics-Constrained Networks (ICML 2025 · similarity 0.85)
- Convolutions and More as Einsum: A Tensor Network Perspective with Advances for Second-Order Methods (NeurIPS 2024 · similarity 0.85)
- Learning Chern Numbers of Multiband Topological Insulators with Gauge Equivariant Neural Networks (NeurIPS 2025 · similarity 0.85)
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.
