arXiv:2604. 27723v2 Announce Type: replace Abstract: Learning algorithms can be significantly improved by routing complex or uncertain inputs to specialized experts, balancing accuracy with computational cost.
arXiv:2604.12411v2 Announce Type: replace Abstract: Segmentation models based on deep neural networks demonstrate strong generalization for medical image segmentation. However, they often exhibit ove...
arXiv:2606. 10250v1 Announce Type: cross Abstract: Class imbalance is a common problem in deep learning that severely degrades performance.
arXiv:2511. 08972v2 Announce Type: replace Abstract: Sparse Mixture-of-Experts (SMoE) models are scalable and computationally efficient, enabling large increases in model capacity with limited inference overhead.
arXiv:2605. 03135v2 Announce Type: replace Abstract: Standard classification treats all errors equally, but in applications such as content moderation and medical screening, mistakes on clear-cut cases are more costly than errors on ambiguous ones.
arXiv:2609.36724v1 Announce Type: new Abstract: Sparse expert models can distribute traffic evenly while still grouping incompatible training signals within the same experts. We study routing as a gr...
Sparse expert models can distribute traffic evenly while still grouping incompatible training signals within the same experts. We study routing as a gradient-partitioning problem and introduce gradien...
The paper investigates the consistency of surrogate loss methods for classification and policy learning when the set of admissible classifiers is constrained, such as by interpretability or fairness requirements. It shows that hinge loss is the only surrogate that preserves consistency when constraints limit only the prediction set, but consistency can fail if constraints also restrict the functional form. The authors derive conditions guaranteeing consistency for hinge-risk-minimizing classifiers and use these results to design efficient hinge-loss-based procedures for monotone classification problems.
arXiv:2609.26384v1 Announce Type: new Abstract: Medical image interpretation is high-volume and time-consuming, and while AI interpretation can reduce workload, fully autonomous deployment carries po...
arXiv:2607. 22258v1 Announce Type: new Abstract: Deep learning models using traditional softmax classifiers have achieved remarkable success in various classification tasks.
arXiv:2606. 28835v1 Announce Type: cross Abstract: Federated Learning (FL) emerged as a promising distributed machine learning paradigm.
arXiv:2608.30699v1 Announce Type: cross Abstract: Long-tailed distributions are prevalent in real-world semi-supervised learning (SSL), where pseudo-labels tend to favor majority classes, leading to...
arXiv:2607. 29462v1 Announce Type: cross Abstract: Adapting deep learning models to profound clinical heterogeneity typically relies on parameter-efficient fine-tuning (PEFT) to avoid the severe overfitting associated with full end-to-end network updates.