arXiv:2607. 16768v1 Announce Type: new Abstract: Learning with noisy labels is a fundamental problem in training reliable deep neural networks.
By Peng Hu, Jianwei Ma
arXiv:2608. 08489v1 Announce Type: new Abstract: Neural network classifiers trained by cross-entropy minimization are highly sensitive to label noise and adversarial contamination.
By Subhabrata Majumdar, Anand Deo, Partha Pratim Saha, Abhik Ghosh
arXiv:2605. 18662v2 Announce Type: replace Abstract: Noise-tolerant PAC learning of linear models has been of central interests in machine learning community since the last century.
By Rita Adhikari, Shiwei Zeng
arXiv:2508. 09697v4 Announce Type: replace Abstract: Noisy labels are inevitable in real-world multimedia applications.
By Xinlei Zhang, Fan Liu, Chuanyi Zhang, Xiaoying Ji, Wenhui Wang, Wei Zhou, Yuhui Zheng
The paper investigates minimal‑norm interpolation and λ2‑regularized logistic‑loss minimization for binary classification using univariate two‑layer ReLU networks. It provides exact geometric characterizations of optimal classifiers, showing that unpenalized hidden‑layer biases yield continuous piecewise‑affine functions that tightly follow label switches, while penalized biases produce a unique, sparsest classifier with a single kink per same‑label segment. Adding a free affine skip connection does not change these function‑space solutions but guarantees that every KKT point becomes globally optimal, eliminating suboptimal KKT points that can arise without the skip connection.
By Karolina Drabik, Ben Lewis, Antoni Puch, Etienne Boursier, Piotr Hofman, Matthias Englert, Ranko Lazi\'c
The paper investigates the impact of label noise on sign language recognition, comparing robust loss functions—symmetric cross entropy (SCE) and generalized cross entropy (GCE)—to standard cross entropy (CE) in both isolated (ISLR) and continuous (CSLR) settings. Experiments on ASL Citizen with injected symmetric noise show that SCE and GCE outperform CE across multiple backbones, though GCE’s optimal hyperparameter does not transfer well. In CSLR experiments on PHOENIX-2014, robust losses offer limited gains, with performance largely influenced by auxiliary weight settings rather than the loss choice.
By Akihisa Shitara, Yoichi Ochiai