Deep Learning
Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers
Zeyuan Allen-Zhu, Yuanzhi Li, Yingyu Liang
Neural Information Processing Systems http://nips.cc/
Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
We design two novel methods to improve performance in such scenarios. First, we propose a theoretically-principled label-distribution-aware margin (LDAM) loss motivated by minimizing a margin-based generalization bound.
Multipole Graph Neural Operator for Parametric Partial Differential Equations
PDEs and can be evaluated in linear time.
Robustness to Adversarial Perturbations in Learning from Incomplete Data
Amir Najafi, Shin-ichi Maeda, Masanori Koyama, Takeru Miyato
Neural Information Processing Systems http://nips.cc/
Autoregressive Score Matching
Compared to previous score matching algorithms, our method is more scalable to high dimensional data and more stable to optimize.
Deep Leakage from Gradients
Ligeng Zhu, Zhijian Liu, Song Han
Distributed training becomes necessary to speedup training on large-scale datasets.