IFW-BLS is a Dual‑Robust Broad Learning System that enhances the standard Broad Learning System by incorporating two robustness mechanisms. It replaces the squared loss with a bounded, smooth, asymmetric wave loss to protect against large residuals, and applies intuitionistic fuzzy scores to weight samples based on global class consistency and local neighborhood conflict, thereby down‑weighting unreliable data. The model is optimized with a Nesterov accelerated gradient solver, avoiding explicit matrix inversion, and experiments on UCI benchmarks show it outperforms baseline models and remains stable under noise and outlier contamination.
By Mushir Akhtar, M. Tanveer
The paper introduces IFW-BLS, a Dual‑Robust Broad Learning System that enhances the traditional BLS by incorporating a bounded, asymmetric wave loss to protect against large residuals and by applying intuitionistic fuzzy scores to weight samples based on credibility. This dual approach mitigates the impact of noise, outliers, and ambiguous data points, while a Nesterov‑accelerated optimizer replaces the costly matrix inversion of conventional BLS. Experiments on UCI benchmarks and corruption tests demonstrate that IFW‑BLS outperforms baseline models and remains more stable under noisy conditions.
arXiv:2606. 16050v1 Announce Type: cross Abstract: Robust deep learning under heavy-tailed and impulsive noise remains challenging because conventional losses such as mean squared error (MSE) exhibit unbounded sensitivity to outliers.
By Mainak Kundu, Ria Kanjilal, Ismail Uysal
arXiv:2606. 22068v2 Announce Type: replace-cross Abstract: Most real-world datasets used for training supervised learning models are contaminated with noisy data and outliers leading to large prediction errors.
By Mathew Mithra Noel, Arindam Banerjee, Yug D. Oswal, Geraldine Bessie Amali D, Venkataraman Muthiah-Nakarajan
arXiv:2607. 06151v1 Announce Type: new Abstract: Generalization remains a pivotal challenge in deep learning, where traditional optimizers like Stochastic Gradient Descent (SGD) often converge to sharp minima, leading to overfitting and reduced performance on unseen data.
By Yao Fu, Chunxia Zhang, Junmin Liu, Yihang Jin, Haishan Ye, Yuanao Yang
arXiv:2609.39489v1 Announce Type: new
Abstract: Sample-level reliability heterogeneity is common in deep time series learning. Standard training pipelines apply a uniform regularization setting to al...
By Siru Zhong, Senzhang Wang, James T. Kwok, Yuxuan Liang