Research map / Learning theory and algorithms / Kernels and regression theory
Transformed Low-Rank Parameterization Can Help Robust Generalization for Tensor Neural Networks
Andong Wang, Chao Li, Mingyuan Bai, Zhong Jin, Guoxu Zhou, Qibin 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 |
|---|---|---|---|
| restrict weight tensors to low tubal rank (4) instead of full tubal rank (28) (ablation) | t-NN with three t-product layers · MNIST 3 vs 7, FGSM 20/255 | adversarial generalization gap | Improved |
| increase training sample size N (ablation) | t-NN adversarial training · MNIST 3 vs 7, FGSM | adversarial generalization gap | Improved |
| run more epochs of adversarial training with SGD on over-parameterized t-NN (D=128, 256) | t-NN · MNIST binary, FGSM | stable rank of weights | Improved |
| add tubal nuclear norm regularizer with weight 0.01 (ablation) | t-NN with D=128 · MNIST binary, FGSM | stable rank of weights | Improved |
Closest papers by meaning
- Stability and Generalization of Adversarial Training for Shallow Neural Networks with Smooth Activation (NeurIPS 2024 · similarity 0.88)
- Dynamical Low-Rank Compression of Neural Networks with Robustness under Adversarial Attacks (NeurIPS 2025 · similarity 0.87)
- Adversarial generalization of unfolding (model-based) networks (NeurIPS 2025 · similarity 0.86)
- Stable Minima of ReLU Neural Networks Suffer from the Curse of Dimensionality: The Neural Shattering Phenomenon (NeurIPS 2025 · similarity 0.86)
- Mixture of Adversarial LoRAs: Boosting Robust Generalization in Meta-Tuning (NeurIPS 2024 · similarity 0.86)
- Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes (NeurIPS 2024 · similarity 0.86)
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.
