Robuta

https://openreview.net/forum?id=n0OeTdNRG0Q Efficient Sharpness-aware Minimization for Improved Training of Neural Networks | OpenReview Overparametrized Deep Neural Networks (DNNs) often achieve astounding performances, but may potentially result in severe generalization error. Recently, the... sharpness aware minimization training of neural networks efficient https://openreview.net/forum?id=ZdVZNk2UF1 Smoothness-Adaptive Sharpness-Aware Minimization for Finding Flatter Minima | OpenReview The sharpness-aware minimization (SAM) procedure recently gained increasing attention due to its favorable generalization ability to unseen data. SAM aims to... sharpness aware minimization smoothness adaptive finding flatter https://openreview.net/forum?id=yL_iq-Q-ORS Perturbing BatchNorm and Only BatchNorm Benefits Sharpness-Aware Minimization | OpenReview Perturbing only the BatchNorm parameters in the adversarial step benefits several SAM-variants. sharpness aware minimization batchnorm benefits openreview https://jmlr.org/papers/v24/23-043.html The Dynamics of Sharpness-Aware Minimization: Bouncing Across Ravines and Drifting Towards Wide... sharpness aware minimization https://jmlr.org/papers/v25/23-1285.html Sharpness-Aware Minimization and the Edge of Stability sharpness aware minimization the edge stability https://openreview.net/forum?id=3WAnGWLpSQ Why Does Sharpness-Aware Minimization Generalize Better Than SGD? | OpenReview The challenge of overfitting, in which the model memorizes the training data and fails to generalize to test data, has become increasingly significant in the... sharpness aware minimization better than generalize sgd openreview https://openreview.net/forum?id=strvrjSi3C Riemannian SAM: Sharpness-Aware Minimization on Riemannian Manifolds | OpenReview Contemporary advances in the field of deep learning have embarked upon an exploration of the underlying geometric properties of data, thus encouraging the... sharpness aware minimization riemannian sam manifolds openreview https://aclanthology.org/2022.findings-emnlp.361/ Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models - ACL... Clara Na, Sanket Vaibhav Mehta, Emma Strubell. Findings of the Association for Computational Linguistics: EMNLP 2022. 2022. sharpness aware minimization https://arxiv.org/abs/2602.06837 [2602.06837] Learning Deep Hybrid Models with Sharpness-Aware Minimization Abstract page for arXiv paper 2602.06837: Learning Deep Hybrid Models with Sharpness-Aware Minimization hybrid models 2602 06837 learning deep https://arxiv.org/abs/2509.02433 [2509.02433] VASSO: Variance Suppression for Sharpness-Aware Minimization Abstract page for arXiv paper 2509.02433: VASSO: Variance Suppression for Sharpness-Aware Minimization 2509 02433 vasso variance suppression