Mitsuki Sakamoto
5 papers · 2022–2025 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(14)
🏆
Keyword Champion
Venues
Top co-authors
Research topics
Mathematics & Optimization
(4)
Optimization
(4)
Artificial Intelligence
(3)
Machine Learning
(3)
Core AI
(3)
Reinforcement Learning
(2)
Learning Types · Machine Learning
(2)
Methods
(2)
Optimization & Theory
(2)
Deep Learning
(1)
Natural Language Processing
(1)
Generation
(1)
Learning Types · Deep Learning
(1)
Models
(1)
Keywords
nash equilibrium
(3)
game theory
(2)
zero-sum game
(2)
last-iterate convergence
(2)
payoff perturbation
(2)
model alignment
(1)
direct preference optimization
(1)
mirror descent
(1)
additive noise
(1)
convergence guarantee
(1)
slingshot strategy
(1)
language model
(1)
optimistic md
(1)
reward model
(1)
first-order method
(1)
gradient ascent
(1)
multiplicative weights update
(1)
noisy gradient
(1)
preference dataset
(1)
text quality
(1)
Papers
Boosting Perturbed Gradient Ascent for Last-Iterate Convergence in Games
ICLR 2025
Adaptively Perturbed Mirror Descent for Learning in Games
ICML 2024
Filtered Direct Preference Optimization
EMNLP 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