Global Convergence and Stability of Stochastic Gradient Descent

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 47 of 50
1. Verfasser: Patel, Vivak (VerfasserIn)
Weitere Verfasser: Zhang, Shushu (VerfasserIn), Tian, Bowen (VerfasserIn)
Pages:36
Format: UnknownFormat
Sprache:eng
Veröffentlicht: 2023
Schlagworte:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Titel Jahr Verfasser
Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions 2023 Paquette, Courtney
Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork 2023 Wang, Haotao
AniFaceGAN: Animatable 3D-Aware Face Image Generation for Video Avatars 2023 Wu, Yue
Detection and Localization of Changes in Conditional Distributions 2023 Nie, Lizhen
Decoupling Features in Hierarchical Propagation for Video Object Segmentation 2023 Yang, Zongxin
Training with More Confidence: Mitigating Injected and Natural Backdoors During Training 2023 Wang, Zhenting
Revisiting Optimal Convergence Rate for Smooth and Non-convex Stochastic Decentralized Optimization 2023 Yuan, Kun
MSDS: A Large-Scale Chinese Signature and Token Digit String Dataset for Handwriting Verification 2023 Zhang, Peirong
Generative multitask learning mitigates target-causing confounding 2023 Makino, Taro
Revisit last-iterate convergence of mSGD under milder requirement on step size 2023 Jin, ruinan
Are You Stealing My Model? Sample Correlation for Fingerprinting Deep Neural Networks 2023 Guan, Jiyang
SecureFedYJ: a safe feature Gaussianization protocol for Federated Learning 2023 Marchand, Tanguy
A Direct Approximation of AIXI Using Logical State Abstractions 2023 Yang-Zhao, Samuel
Learning Representations via a Robust Behavioral Metric for Deep Reinforcement Learning 2023 Chen, Jianda
Finding Second-Order Stationary Points in Nonconvex-Strongly-Concave Minimax Optimization 2023 Luo, Luo
Masked Autoencoders As Spatiotemporal Learners 2023 Feichtenhofer, Christoph
On the Parameterization and Initialization of Diagonal State Space Models 2023 Gu, Albert
Rethinking Alignment in Video Super-Resolution Transformers 2023 Shi, Shuwei
Learning to Scaffold: Optimizing Model Explanations for Teaching 2023 Fernandes, Patrick
Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization) 2023 Zhu, Zhenyu
Alle Artikel auflisten