Mitsuki Sakamoto

16 papers A* 3A 2Journal 11
YearRankTypeTitle / Venue / Authors
2025 A* conf
Boosting Perturbed Gradient Ascent for Last-Iterate Convergence in Games.
ICLR
Kenshi Abe, Mitsuki Sakamoto, Kaito Ariu, Atsushi Iwasaki
2025 J jnl
Evaluation of Best-of-N Sampling Strategies for Language Model Alignment.
CoRR
Yuki Ichihara, Yuu Jinnai, Tetsuro Morimura, Kaito Ariu, Kenshi Abe, Mitsuki Sakamoto, Eiji Uchibe
2025 J jnl
Evaluation of Best-of-N Sampling Strategies for Language Model Alignment.
Trans. Mach. Learn. Res.
Yuki Ichihara, Yuu Jinnai, Tetsuro Morimura, Kenshi Abe, Kaito Ariu, Mitsuki Sakamoto, Eiji Uchibe
2025 J jnl
MO-GRPO: Mitigating Reward Hacking of Group Relative Policy Optimization on Multi-Objective Problems.
CoRR
Yuki Ichihara, Yuu Jinnai, Tetsuro Morimura, Mitsuki Sakamoto, Ryota Mitsuhashi, Eiji Uchibe
2025 J jnl
The Power of Perturbation under Sampling in Solving Extensive-Form Games.
CoRR
Wataru Masaka, Mitsuki Sakamoto, Kenshi Abe, Kaito Ariu, Tuomas Sandholm, Atsushi Iwasaki
2024 A* conf
Adaptively Perturbed Mirror Descent for Learning in Games.
ICML
Kenshi Abe, Kaito Ariu, Mitsuki Sakamoto, Atsushi Iwasaki
2024 J jnl
Boosting Perturbed Gradient Ascent for Last-Iterate Convergence in Games.
CoRR
Kenshi Abe, Mitsuki Sakamoto, Kaito Ariu, Atsushi Iwasaki
2024 A* conf
Filtered Direct Preference Optimization.
EMNLP
Tetsuro Morimura, Mitsuki Sakamoto, Yuu Jinnai, Kenshi Abe, Kaito Ariu
2024 J jnl
Filtered Direct Preference Optimization.
CoRR
Tetsuro Morimura, Mitsuki Sakamoto, Yuu Jinnai, Kenshi Abe, Kaito Ariu
2023 J jnl
A Slingshot Approach to Learning in Monotone Games.
CoRR
Kenshi Abe, Kaito Ariu, Mitsuki Sakamoto, Atsushi Iwasaki
2023 A conf
Last-Iterate Convergence with Full and Noisy Feedback in Two-Player Zero-Sum Games.
AISTATS
Kenshi Abe, Kaito Ariu, Mitsuki Sakamoto, Kentaro Toyoshima, Atsushi Iwasaki
2022 J jnl
Last-Iterate Convergence with Full- and Noisy-Information Feedback in Two-Player Zero-Sum Games.
CoRR
Kenshi Abe, Kaito Ariu, Mitsuki Sakamoto, Kentaro Toyoshima, Atsushi Iwasaki
2022 J jnl
Mutation-Driven Follow the Regularized Leader for Last-Iterate Convergence in Zero-Sum Games.
CoRR
Kenshi Abe, Mitsuki Sakamoto, Atsushi Iwasaki
2022 A conf
Mutation-driven follow the regularized leader for last-iterate convergence in zero-sum games.
UAI
Kenshi Abe, Mitsuki Sakamoto, Atsushi Iwasaki
2020 J jnl
Bayesian Segmentation of Hip and Thigh Muscles in Metal Artifact-Contaminated CT Using Convolutional Neural Network-Enhanced Normalized Metal Artifact Reduction.
J. Signal Process. Syst.
Mitsuki Sakamoto, Yuta Hiasa, Yoshito Otake, Masaki Takao, Yuki Suzuki, Nobuhiko Sugano, Yoshinobu Sato
2019 J jnl
Automated Segmentation of Hip and Thigh Muscles in Metal Artifact-Contaminated CT using Convolutional Neural Network-Enhanced Normalized Metal Artifact Reduction.
CoRR
Mitsuki Sakamoto, Yuta Hiasa, Yoshito Otake, Masaki Takao, Yuki Suzuki, Nobuhiko Sugano, Yoshinobu Sato