Yannan Chen, Liqun Qi, Qun Wang
In this note, we construct explicit SOS decomposition of A Fourth Order Four Dimensional Hankel Tensor with A Symmetric Generating Vector, at the critical value. This is a supplementary note to Paper [3].
Yannan Chen, Ruoyu Chen, Bin Zeng et al.
In current visual model training, models often rely on only limited sufficient causes for their predictions, which makes them sensitive to distribution shifts or the absence of key features. Attribution methods can accurately identify a model's critical regions. However, masking these areas to create counterfactuals often causes the model to misclassify the target, while humans can still easily recognize it. This divergence highlights that the model's learned dependencies may not be sufficiently causal. To address this issue, we propose Subset-Selected Counterfactual Augmentation (SS-CA), which integrates counterfactual explanations directly into the training process for targeted intervention. Building on the subset-selection-based LIMA attribution method, we develop Counterfactual LIMA to identify minimal spatial region sets whose removal can selectively alter model predictions. Leveraging these attributions, we introduce a data augmentation strategy that replaces the identified regions with natural background, and we train the model jointly on both augmented and original samples to mitigate incomplete causal learning. Extensive experiments across multiple ImageNet variants show that SS-CA improves generalization on in-distribution (ID) test data and achieves superior performance on out-of-distribution (OOD) benchmarks such as ImageNet-R and ImageNet-S. Under perturbations including noise, models trained with SS-CA also exhibit enhanced generalization, demonstrating that our approach effectively uses interpretability insights to correct model deficiencies and improve both performance and robustness.
Yannan Chen, Liqun Qi, Qun Wang
Large scale tensors, including large scale Hankel tensors, have many applications in science and engineering. In this paper, we propose an inexact curvilinear search optimization method to compute Z- and H-eigenvalues of $m$th order $n$ dimensional Hankel tensors, where $n$ is large. Owing to the fast Fourier transform, the computational cost of each iteration of the new method is about $\mathcal{O}(mn\log(mn))$. Using the Cayley transform, we obtain an effective curvilinear search scheme. Then, we show that every limiting point of iterates generated by the new algorithm is an eigen-pair of Hankel tensors. Without the assumption of a second-order sufficient condition, we analyze the linear convergence rate of iterate sequence by the Kurdyka-Łojasiewicz property. Finally, numerical experiments for Hankel tensors, whose dimension may up to one million, are reported to show the efficiency of the proposed curvilinear search method.