Asynchronous SGD Beats Minibatch SGD Under Arbitrary Delays

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 1 of 50
1. Verfasser: Mishchenko, Konstantin (VerfasserIn)
Weitere Verfasser: Bach, Francis (VerfasserIn), Even, Mathieu (VerfasserIn), Woodworth, Blake E (VerfasserIn)
Pages:36
Format: UnknownFormat
Sprache:eng
Veröffentlicht: 2023
Schlagworte:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Titel Jahr Verfasser
Federated Submodel Optimization for Hot and Cold Data Features 2023 Ding, Yucheng
Fast Bayesian Coresets via Subsampling and Quasi-Newton Refinement 2023 Naik, Cian
Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning 2023 Lian, Dongze
Offline Goal-Conditioned Reinforcement Learning via f-Advantage Regression 2023 Ma, Jason Yecheng
Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation 2023 Zhong, Zhun
Rethinking and Improving Robustness of Convolutional Neural Networks: a Shapley Value-based Approach in Frequency Domain 2023 Chen, Yiting
Wavelet Score-Based Generative Modeling 2023 Guth, Florentin
Generalizing Consistent Multi-Class Classification with Rejection to be Compatible with Arbitrary Losses 2023 Cao, Yuzhou
IM-Loss: Information Maximization Loss for Spiking Neural Networks 2023 Guo, Yufei
Offline Multi-Agent Reinforcement Learning with Knowledge Distillation 2023 Tseng, Wei-Cheng
Conditional Meta-Learning of Linear Representations 2023 Denevi, Giulia
Diffusion Visual Counterfactual Explanations 2023 Augustin, Maximilian
On-Demand Sampling: Learning Optimally from Multiple Distributions 2023 Haghtalab, Nika
A Consolidated Cross-Validation Algorithm for Support Vector Machines via Data Reduction 2023 Wang, Boxiang
Recurrent Video Restoration Transformer with Guided Deformable Attention 2023 Liang, Jingyun
Generating Training Data with Language Models: Towards Zero-Shot Language Understanding 2023 Meng, Yu
Why do tree-based models still outperform deep learning on typical tabular data? 2023 Grinsztajn, Leo
Structured Recognition for Generative Models with Explaining Away 2023 Yu, Changmin
Zero-Shot Video Question Answering via Frozen Bidirectional Language Models 2023 Yang, Antoine
Active Learning with Neural Networks: Insights from Nonparametric Statistics 2023 Zhu, Yinglun
Alle Artikel auflisten