I’m Yuki Takezawa, a 2nd year master’s student at Kashima Yamada Laboratory, Kyoto University.

Research interests: Machine Learning, Optimal Transport, Distributed Optimization.

contact: yuki-takezawa at ml.ist.i.kyoto-u.ac.jp

dblp / google scholar

Publications

Conference Papers

  1. Yuki Takezawa, Ryoma Sato, Zornitsa Kozareva, Sujith Ravi, Makoto Yamada, “Fixed Support Tree-Sliced Wasserstein Barycenter”, AISTATS 2022
  2. Yuki Takezawa, Ryoma Sato, Makoto Yamada, “Supervised Tree-Wasserstein Distance”, ICML 2021

Journal Papers

  1. Makoto Yamada, Yuki Takezawa, Ryoma Sato, Han Bao, Zornitsa Kozareva, Sujith Ravi, “Approximating 1-Wasserstein Distance with Trees”, Transactions of Machine Learning Research 2022

Preprints

  1. Yuki Takezawa, Han Bao, Kenta Niwa, Ryoma Sato, Makoto Yamada, “Momentum Tracking: Momentum Acceleration for Decentralized Deep Learning on Heterogeneous Data”, arXiv 2022
  2. Yuki Takezawa, Kenta Niwa, Makoto Yamada, “Communication Compression for Decentralized Learning with Operator Splitting Methods”, arXiv 2022
  3. Yuki Takezawa, Kenta Niwa, Makoto Yamada, “Theoretical Analysis of Primal-Dual Algorithm for Non-Convex Stochastic Decentralized Optimization”, arXiv 2022

Research Experiences

Honor

Education

Activity


Yuki Takezawa (c) 2021