Scholar
Yuki Takezawa
Google Scholar ID: eaKQb8IAAAAJ
Kyoto University / OIST
Citations & Impact
Citations
184
H-index
8
i10-index
8
Publications
20
Co-authors
23
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Conference Papers:
- - “Any-stepsize Gradient Descent for Separable Data under Fenchel–Young Losses”, NeurIPS 2025
- - “Revisiting 1-peer Exponential Graph for Enhancing Decentralized Learning Efficiency”, NeurIPS 2025
- - “Exploiting Similarity for Computation and Communication-Efficient Decentralized Optimization”, ICML 2025
- - “Scalable Decentralized Learning with Teleportation”, ICLR 2025
- - “PhiNets: Brain-inspired Non-contrastive Learning Based on Temporal Prediction Hypothesis”, ICLR 2025
- - “Parameter-free Clipped Gradient Descent Meets Polyak”, NeurIPS 2024
- - “Large-scale Similarity Search with Optimal Transport”, EMNLP 2023
- - “Beyond Exponential Graph: Communication-Efficient Topologies for Decentralized Learning via Finite-time Convergence”, NeurIPS 2023
- - “Improving the Robustness to Variations of Objects and Instructions with A Neuro-Symbolic Approach for Interactive Instruction Following”, ICMM 2023
- - “Fixed Support Tree-Sliced Wasserstein Barycenter”, AISTATS 2022
- - “Supervised Tree-Wasserstein Distance”, ICML 2021
- Journal Papers:
- - “A Bias Correction Mechanism for Distributed Asynchronous Optimization”, Transactions on Machine Learning Research 2025
- - “Necessary and Sufficient Watermark for Large Language Models”, Transactions on Machine Learning Research 2025
- - “An Empirical Study of Simplicial Representation Learning with Wasserstein Distance”, Entropy 2024
- - “A Localized Primal-Dual Method for Centralized/Decentralized Federated Learning Robust to Data Heterogeneity”, IEEE Transactions on Signal and Information Processing over Networks 2023
- - “Momentum Tracking: Momentum Acceleration for Decentralized Deep Learning on Heterogeneous Data”, Transactions on Machine Learning Research 2023
- - “Communication Compression for Decentralized Learning with Operator Splitting Methods”, IEEE Transactions on Signal and Information Processing over Networks 2023
Research Experience
- Work Experience:
- - Visiting Research Student, Yamada Unit, Okinawa Institute of Science and Technology
- - Ph.D. Student, Kashima Laboratory, Kyoto University
Education
- Degree: Ph.D.
- University: Kyoto University
- Advisor: Not explicitly mentioned
- Time: Ongoing
- Field: Not explicitly mentioned
Background
- Research interests: Machine Learning, Optimization, Optimal Transport. 3rd year Ph.D. student at Kashima Laboratory, Kyoto University. Also working as a visiting research student at Yamada Unit, Okinawa Institute of Science and Technology.
