Analysing heavy-tail properties of Stochastic Gradient Descent by means of Stochastic Recurrence Equationsby Ewa Damek,…
ADEdgeDrop: Adversarial Edge Dropping for Robust Graph Neural Networksby Zhaoliang Chen, Zhihao Wu, Ylli Sadikaj,…
Effective Gradient Sample Size via Variation Estimation for Accelerating Sharpness aware Minimizationby Jiaxin Deng, Junbiao…
Improving Implicit Regularization of SGD with Preconditioning for Least Square Problemsby Junwei Su, Difan Zou,…
Efficient Language Model Architectures for Differentially Private Federated Learningby Jae Hun Ro, Srinadh Bhojanapalli, Zheng…
Do Deep Neural Network Solutions Form a Star Domain?by Ankit Sonthalia, Alexander Rubinstein, Ehsan Abbasnejad,…
Fairness Feedback Loops: Training on Synthetic Data Amplifies Biasby Sierra Wyllie, Ilia Shumailov, Nicolas PapernotFirst…
SGD with Partial Hessian for Deep Neural Networks Optimizationby Ying Sun, Hongwei Yong, Lei ZhangFirst…
The Implicit Bias of Heterogeneity towards Invariance: A Study of Multi-Environment Matrix Sensingby Yang Xu,…
Transformers for Supervised Online Continual Learningby Jorg Bornschein, Yazhe Li, Amal Rannen-TrikiFirst submitted to arxiv…