Skip to content

Slaw: sharpness- and loss-adaptive weighting for robust deep learning

Sep 2026 · International Journal of Data Science and Analysis · Vol 22 · 0 citations · 42 references

TL;DR

Results show the applicability and efficiency of SLAW in building reliable deep learning systems that are appropriate for real-world use, where data is often imperfect, noisy, or of a low quality.

View source

Similar papers

Oct 2026

Gradient-Modulated Cross-Entropy Loss for Robust Learning With Label Noise.

Deep neural networks (DNNs) trained with the standard cross-entropy (CE) loss typically achieve strong performance on clean datasets but suffer from severe overfitting when confronted with label noise. To alleviate this issue, numerous robust loss functions have been proposed and shown to improve noise tolerance. Howev...

Lin Wang, Fang Liu, Xiang-Min Xu et al. · 0 citations
Preprint Oct 2026

Curvature-Scaled Sharpness-Aware Minimization: Convergence Beyond Smoothness

This work uses relative gradient distortion to quantify how the sharpness-aware direction departs from the original gradient and proposes Curvature-Scaled SAM (CS-SAM), which scales both the perturbation and the descent step by suitable curvature upper bounds, and proves that it uniformly bounds the distortion.

Dimitris Oikonomou, Nicolas Loizou · 0 citations
Conference Open access Jun 2026

Sparsity-Adaptive Sharpness-Aware Minimization

Sparsity-Adaptive Sharpness-Aware Minimization (SA-SAM), which derives a sparsity-dependent SAM/ASAM perturbation radius by keeping the mean absolute perturbation approximately invariant as sparsity increases, is introduced.

Shiryu Ueno, Yoshikazu Hayashi, Kunihito Kato · 0 citations
#artificial intelligence Preprint Oct 2026

One Size Does Not Fit All: Curvature-Aware Adaptive Perturbation for SAM

Poor generalisation in deep neural networks is frequently associated with convergence to sharp minima. Sharpness-Aware Minimisation (SAM) improves generalisation of deep neural networks by minimising a combination of the training loss and the local sharpness of the loss landscape, biasing convergence towards flat minim...

Alessia Rossi, F. Campelo, Gabriel L. Oliveira · 0 citations
Open access Oct 2026

Stable Image Regression via Adaptive Aggregation of Noisy Predictions and Input-Gradient-Regularized Fine-Tuning

Image regression models may exhibit substantial output variation under small input perturbations, which can reduce their reliability in applications requiring continuous predictions. This study investigates whether adaptive aggregation of noise-perturbed predictions, combined with explicit control of model sensitivity,...

E. Shumitskaya, D. Vatolin, Anastasia Antsiferova · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.