Filter by Keyword:

30 Results

Oral
Tue 17:00 Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning
Shariq Iqbal, Christian Schroeder, Bei Peng, Wendelin Boehmer, Shimon Whiteson, Fei Sha
Oral
Tue 17:00 A Tale of Two Efficient and Informative Negative Sampling Distributions
Shabnam Daghaghi, Tharun Medini, Nicholas Meisburger, Beidi Chen, Mengnan Zhao, Anshumali Shrivastava
Spotlight
Tue 17:20 TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models
Zhuohan Li, Siyuan Zhuang, Shiyuan Guo, Danyang Zhuo, Hao Zhang, Dawn Song, Ion Stoica
Spotlight
Wed 9:25 Quantization Algorithms for Random Fourier Features
Xiaoyun Li, Ping Li
Spotlight
Wed 9:40 Partially Observed Exchangeable Modeling
Yang Li, Junier Oliva
Spotlight
Tue 17:40 Heterogeneity for the Win: One-Shot Federated Clustering
Don Kurian Dennis, Tian Li, Virginia Smith
Spotlight
Wed 10:25 A Unified Generative Adversarial Network Training via Self-Labeling and Self-Attention
Tomoki Watanabe, Paolo Favaro
Spotlight
Wed 10:40 Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics
Vivek Jayaram, John Thickstun
Oral
Tue 19:00 ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training
Jianfei Chen, Lianmin Zheng, Zhewei Yao, Dequan Wang, Ion Stoica, Michael Mahoney, Joseph E Gonzalez
Spotlight
Tue 19:30 Training Graph Neural Networks with 1000 Layers
Guohao Li, Matthias Müller, Bernard Ghanem, Vladlen Koltun
Spotlight
Tue 19:35 1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed
Hanlin Tang, Shaoduo Gan, Ammar Ahmad Awan, Samyam Rajbhandari, Conglong Li, Xiangru Lian, Ji Liu, Ce Zhang, Yuxiong He
Spotlight
Wed 11:45 Ditto: Fair and Robust Federated Learning Through Personalization
Tian Li, Shengyuan Hu, Ahmad Beirami, Virginia Smith
Poster
Wed 13:00 Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics
Vivek Jayaram, John Thickstun
Poster
Tue 21:00 A Tale of Two Efficient and Informative Negative Sampling Distributions
Shabnam Daghaghi, Tharun Medini, Nicholas Meisburger, Beidi Chen, Mengnan Zhao, Anshumali Shrivastava
Poster
Tue 21:00 1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed
Hanlin Tang, Shaoduo Gan, Ammar Ahmad Awan, Samyam Rajbhandari, Conglong Li, Xiangru Lian, Ji Liu, Ce Zhang, Yuxiong He
Poster
Tue 21:00 Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning
Shariq Iqbal, Christian Schroeder, Bei Peng, Wendelin Boehmer, Shimon Whiteson, Fei Sha
Poster
Tue 21:00 ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training
Jianfei Chen, Lianmin Zheng, Zhewei Yao, Dequan Wang, Ion Stoica, Michael Mahoney, Joseph E Gonzalez
Poster
Wed 13:00 Partially Observed Exchangeable Modeling
Yang Li, Junier Oliva
Poster
Tue 21:00 TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models
Zhuohan Li, Siyuan Zhuang, Shiyuan Guo, Danyang Zhuo, Hao Zhang, Dawn Song, Ion Stoica
Poster
Wed 13:00 Ditto: Fair and Robust Federated Learning Through Personalization
Tian Li, Shengyuan Hu, Ahmad Beirami, Virginia Smith
Poster
Wed 13:00 Quantization Algorithms for Random Fourier Features
Xiaoyun Li, Ping Li
Poster
Tue 21:00 Heterogeneity for the Win: One-Shot Federated Clustering
Don Kurian Dennis, Tian Li, Virginia Smith
Poster
Tue 21:00 Training Graph Neural Networks with 1000 Layers
Guohao Li, Matthias Müller, Bernard Ghanem, Vladlen Koltun
Poster
Wed 13:00 A Unified Generative Adversarial Network Training via Self-Labeling and Self-Attention
Tomoki Watanabe, Paolo Favaro
Spotlight
Thu 10:30 Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances
Berfin Simsek, François Ged, Arthur Jacot, Francesco Spadaro, Clement Hongler, Wulfram Gerstner, Johanni Brea
Poster
Thu 13:00 Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances
Berfin Simsek, François Ged, Arthur Jacot, Francesco Spadaro, Clement Hongler, Wulfram Gerstner, Johanni Brea
Spotlight
Thu 6:40 Efficient Training of Robust Decision Trees Against Adversarial Examples
Daniël Vos, Sicco Verwer
Spotlight
Thu 7:40 Bayesian Quadrature on Riemannian Data Manifolds
Christian Fröhlich, Alexandra Gessner, Philipp Hennig, Bernhard Schölkopf, Georgios Arvanitidis
Poster
Thu 9:00 Bayesian Quadrature on Riemannian Data Manifolds
Christian Fröhlich, Alexandra Gessner, Philipp Hennig, Bernhard Schölkopf, Georgios Arvanitidis
Poster
Thu 9:00 Efficient Training of Robust Decision Trees Against Adversarial Examples
Daniël Vos, Sicco Verwer