Mitsuki Sakamoto
5 papers · 2022–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Interdisciplinary Bridge
π
Conference Polyglot
(5)
π
Cross-Pollinator
(9)
π
Renaissance Researcher
(6)
πΊοΈ
Taxonomy Completionist
(14)
Conferences
AISTATS (1)
EMNLP (1)
ICLR (1)
ICML (1)
UAI (1)
Top co-authors
Keywords
nash equilibrium
(2)
zero-sum game
(2)
language model alignment
(1)
reinforcement learning from human feedback
(1)
model alignment
(1)
convergence guarantee
(1)
language model
(1)
last-iterate convergence
(1)
reward model
(1)
multiplicative weights update
(1)
noisy gradient
(1)
preference dataset
(1)
text quality
(1)
game theory
(1)
noisy feedback
(1)
direct preference optimization
(1)
Papers
Boosting Perturbed Gradient Ascent for Last-Iterate Convergence in Games
ICLR 2025
Filtered Direct Preference Optimization
EMNLP 2024
Adaptively Perturbed Mirror Descent for Learning in Games
ICML 2024
Last-Iterate Convergence with Full and Noisy Feedback in Two-Player Zero-Sum Games
AISTATS 2023
Mutation-driven follow the regularized leader for last-iterate convergence in zero-sum games
UAI 2022