Beyond Exponential Graph: Communication-Efficient Topologies for Decentralized Learning via Finite-time Convergence

Yuki Takezawa, Ryoma Sato, Han Bao 0002, Kenta Niwa, Makoto Yamada. Beyond Exponential Graph: Communication-Efficient Topologies for Decentralized Learning via Finite-time Convergence. In Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, Sergey Levine, editors, Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023. 2023. [doi]

Authors

Yuki Takezawa

This author has not been identified. Look up 'Yuki Takezawa' in Google

Ryoma Sato

This author has not been identified. Look up 'Ryoma Sato' in Google

Han Bao 0002

This author has not been identified. Look up 'Han Bao 0002' in Google

Kenta Niwa

This author has not been identified. Look up 'Kenta Niwa' in Google

Makoto Yamada

This author has not been identified. Look up 'Makoto Yamada' in Google