Takumi Fukami

Researcher, NTT Corporation

Joined

April 2022

Names

Takumi Fukami (Preferred)

Emails

****@ntt.com (Confirmed)

Personal Links

Career & Education History

Researcher

NTT Corporation (ntt.co.jp)

2020 – Present

Advisors, Relations & Conflicts

No relations added

Expertise

No areas of expertise listed

Publications

FedProx-based heterogeneity-aware parameter-free federated learning
Kenta Niwa, Tomoya Murata, Takumi Fukami
- Submitted to ICLR 2026
- Readers: Everyone
Adaptive Clipping for Differential Private Federated Learning in Interpolation Regimes
Takumi Fukami, Tomoya Murata, Kenta Niwa
- Accepted by TMLR
- Readers: Everyone
Plausible Token Amplification for Improving Accuracy of Differentially Private In-Context Learning Based on Implicit Bayesian Inference
Yusuke Yamasaki, Kenta Niwa, Daiki Chijiwa, Takumi Fukami, Takayuki Miura
- ICML 2025 poster
- Readers: Everyone
NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQA
Marlon Tobaben, Mohamed Ali Souibgui, Rubèn Tito, Khanh Nguyen, Raouf Kerkouche, Kangsoo Jung, Joonas Jälkö, Lei Kang, Andrey Barsky, Vincent Poulain d'Andecy, Aurélie JOSEPH, Aashiq Muhamed, Kevin Kuo, Virginia Smith, Yusuke Yamasaki, Takumi Fukami, Kenta Niwa, Iifan Tyou, Hiro Ishii, Rio Yokota et al. (7 additional authors not shown)
- Accepted by TMLR
- Readers: Everyone
NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQA
Marlon Tobaben, Mohamed Ali Souibgui, Rubèn Tito, Khanh Nguyen, Raouf Kerkouche, Kangsoo Jung, Joonas Jälkö, Lei Kang, Andrey Barsky, Vincent Poulain d'Andecy, Aurélie JOSEPH, Aashiq Muhamed, Kevin Kuo, Virginia Smith, Yusuke Yamasaki, Takumi Fukami, Kenta Niwa, Iifan Tyou, Hiro Ishii, Rio Yokota et al. (7 additional authors not shown)
- Submitted to NeurIPS 2024 Track Datasets and Benchmarks
- Readers: Everyone
Simple Minimax Optimal Byzantine Robust Algorithm for Nonconvex Objectives with Uniform Gradient Heterogeneity
Tomoya Murata, Kenta Niwa, Takumi Fukami, Iifan Tyou
- ICLR 2024 poster
- Readers: Everyone

Co-Authors

View all 29 co-authors

Takumi Fukami

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

FedProx-based heterogeneity-aware parameter-free federated learning

Adaptive Clipping for Differential Private Federated Learning in Interpolation Regimes

Plausible Token Amplification for Improving Accuracy of Differentially Private In-Context Learning Based on Implicit Bayesian Inference

NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQA

NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQA

Simple Minimax Optimal Byzantine Robust Algorithm for Nonconvex Objectives with Uniform Gradient Heterogeneity

Co-Authors