arXiv:2607. 22258v1 Announce Type: new Abstract: Deep learning models using traditional softmax classifiers have achieved remarkable success in various classification tasks.
arXiv:2607. 09832v1 Announce Type: new Abstract: Long-tailed recognition methods often modify losses, margins, or representations to reduce the dominance of frequent classes.
The paper introduces soft‑label‑based estimators for the Bayes‑optimal balanced error rate (BER) and area under the ROC curve (AUC), extending from a clean setting with known class priors to a realistic scenario with unknown priors and corrupted soft labels. It also adapts the FeeBee evaluation framework to assess these estimators without needing the true optimum, providing practical evaluation scores for any estimator of optimal BER or AUC. Experiments on synthetic and real datasets confirm the effectiveness of both the estimators and the evaluation method.
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:2512. 19905v3 Announce Type: replace-cross Abstract: Recent developments in large language models have shown advantages in reallocating a notable share of computational resource from training time to inference time.
arXiv:2610.27443v1 Announce Type: new Abstract: Set-valued classification (SVC) offers a practical approach to communicating uncertainty while maintaining accuracy by predicting variable-sized sets p...
arXiv:2606. 11761v1 Announce Type: new Abstract: Dynamic data pruning techniques aim to reduce computational cost while minimizing information loss by periodically selecting representative subsets of input data during model training.
arXiv:2606. 26053v1 Announce Type: cross Abstract: Synthetic data augmentation is widely used to mitigate class imbalance, but its theoretical effects on score-based classification remain poorly understood.
The paper benchmarks six long‑tail loss functions—cross‑entropy, weighted CE, class‑balanced loss, focal loss, LDAM, and logit‑adjusted softmax—across three single‑cell foundation model architectures (scGPT, scBERT, Geneformer) and three datasets (Multiple Sclerosis, Zheng68K, human Pancreas). It shows that overall accuracy masks systematic failures on rare, disease‑relevant cell types, with a consistent gap between overall accuracy, Macro‑F1, and rare‑class recall under plain cross‑entropy. The study identifies two distinct regimes of rare‑class failure, predicts reweighting efficacy by absolute training‑set size, and finds class‑balanced loss and LDAM to be the most reliable across all settings.
arXiv:2610.28025v1 Announce Type: cross Abstract: This paper studies the problem of aggregation in multiclass classification, generalizing existing results for binary classification. Given a finite d...
arXiv:2609.16365v1 Announce Type: cross Abstract: Real-world datasets often exhibit long-tailed class distributions, where a few head classes contain a large number of training samples while a large...
Prior Fitted Networks (PFNs) such as TabPFN now rival established statistical procedures across prediction and estimation tasks. A natural explanation is that PFNs have the property of statistical ada...