Can overfitted deep neural networks in adversarial training generalize? – An approximation viewpointby Zhongjie Shi,…
How to Collaborate: Towards Maximizing the Generalization Performance in Cross-Silo Federated Learningby Yuchang Sun, Marios…
Unsupervised Learning Method for the Wave Equation Based on Finite Difference Residual Constraints Lossby Xin…
A Precise Characterization of SGD Stability Using Loss Surface Geometryby Gregory Dexter, Borja Ocejo, Sathiya…
VC dimension of Graph Neural Networks with Pfaffian activation functionsby Giuseppe Alessio D'Inverno, Monica Bianchini,…
The Dimension Strikes Back with Gradients: Generalization of Gradient Methods in Stochastic Convex Optimizationby Matan…
Momentum-SAM: Sharpness Aware Minimization without Computational Overheadby Marlon Becker, Frederick Altrock, Benjamin RisseFirst submitted to…
Extracting Formulae in Many-Valued Logic from Deep Neural Networksby Yani Zhang, Helmut BölcskeiFirst submitted to…
Exploring Simple Open-Vocabulary Semantic Segmentationby Zihang LaiFirst submitted to arxiv on: 22 Jan 2024CategoriesMain: Computer…
Memorization in Self-Supervised Learning Improves Downstream Generalizationby Wenhao Wang, Muhammad Ahmad Kaleem, Adam Dziedzic, Michael…