I’m Yuki Takezawa (竹澤祐貴), a 2nd year Ph.D. student at Kashima Laboratory, Kyoto University. I’m also working as a visiting research student at Yamada Unit, Okinawa Institute of Science and Technology.
Research interests: Machine Learning, Optimization, Optimal Transport.
contact: yuki-takezawa at ml.ist.i.kyoto-u.ac.jp
dblp / google scholar / semantic scholar / CV
Yuki Takezawa, Han Bao, Ryoma Sato, Kenta Niwa, Makoto Yamada
“Polyak Meets Parameter-free Clipped Gradient Descent”
Neural Information Processing Systems (NeurIPS) 2024
Cléa Laouar, Yuki Takezawa, Makoto Yamada
“Large-scale Similarity Search with Optimal Transport”
Empirical Methods in Natural Language Processing (EMNLP) 2023
Yuki Takezawa, Ryoma Sato, Han Bao, Kenta Niwa, Makoto Yamada
“Beyond Exponential Graph: Communication-Efficient Topologies for Decentralized Learning via Finite-time Convergence”
Neural Information Processing Systems (NeurIPS) 2023
[slides][poster][code]
Kazutoshi Shinoda, Yuki Takezawa, Masahiro Suzuki, Yusuke Iwasawa, Yutaka Matsuo
“Improving the Robustness to Variations of Objects and Instructions with A Neuro-Symbolic Approach for Interactive Instruction Following”
International Conference on Multimedia Modeling 2023
Yuki Takezawa, Ryoma Sato, Zornitsa Kozareva, Sujith Ravi, Makoto Yamada
“Fixed Support Tree-Sliced Wasserstein Barycenter”
International Conference on Artificial Intelligence and Statistics (AISTATS) 2022
[poster][code]
Yuki Takezawa, Ryoma Sato, Makoto Yamada
“Supervised Tree-Wasserstein Distance”
International Conference on Machine Learning (ICML) 2021
[poster][code]
Iifan Tyou, Tomoya Murata, Takumi Fukami, Yuki Takezawa, Kenta Niwa
“A Localized Primal-Dual Method for Centralized/Decentralized Federated Learning Robust to Data Heterogeneity”
IEEE Transactions on Signal and Information Processing over Networks 2023
Yuki Takezawa, Han Bao, Kenta Niwa, Ryoma Sato, Makoto Yamada
“Momentum Tracking: Momentum Acceleration for Decentralized Deep Learning on Heterogeneous Data”
Transactions on Machine Learning Research 2023
Yuki Takezawa, Kenta Niwa, Makoto Yamada
“Communication Compression for Decentralized Learning with Operator Splitting Methods”
IEEE Transactions on Signal and Information Processing over Networks 2023
Makoto Yamada, Yuki Takezawa, Ryoma Sato, Han Bao, Zornitsa Kozareva, Sujith Ravi
“Approximating 1-Wasserstein Distance with Trees”
Transactions on Machine Learning Research 2022
Satoki Ishikawa, Makoto Yamada, Han Bao, Yuki Takezawa
PhiNets: Brain-inspired Non-contrastive Learning Based on Temporal Prediction Hypothesis, arXiv 2024
Makoto Yamada, Yuki Takezawa, Guillaume Houry, Kira Michaela Dusterwald, Deborah Sulem, Han Zhao, Yao-Hung Hubert Tsai
“An Empirical Study of Simplicial Representation Learning with Wasserstein Distance”, arXiv 2023
Ryoma Sato, Yuki Takezawa, Han Bao, Kenta Niwa, Makoto Yamada
“Embarrassingly Simple Text Watermarks”, arXiv 2023
[demo]
Yuki Takezawa, Ryoma Sato, Han Bao, Kenta Niwa, Makoto Yamada
“Necessary and Sufficient Watermark for Large Language Models”, arXiv 2023
[code]
Yuki Takezawa, Kenta Niwa, Makoto Yamada
“Theoretical Analysis of Primal-Dual Algorithm for Non-Convex Stochastic Decentralized Optimization”, arXiv 2022