Shinji Ito

21 papers at tracked venues · 9 at CORE A* · active 2024–2026

DBLP profile ↗ORCID search ↗

Venues

COLT ×8 NeurIPS ×7 ECML-PKDD ×2 AAAI ×1 AISTATS ×1 ICML ×1 IJCAI ×1

Frequent coauthors

Taira Tsuchiya

×8

Junya Honda

×7

Haipeng Luo

×4

Jongyeong Lee

×3

Arnab Maiti

×2

Yue Wu

×2

Hanna Sumita

×2

Min-hwan Oh

×2

Zachary Chase

×1

Idan Mehalel

×1

Chansoo Kim

×1

Kevin G. Jamieson

×1

Papers

A Tight Lower Bound for Non-stochastic Multi-armed Bandits with Expert Advice
COLT 2026 ·
Zachary Chase
, Shinji Ito,
Idan Mehalel
Adaptive Learning Rates with Surrogate Probability for Follow-the-Perturbed-Leader
COLT 2026 ·
Jongyeong Lee
,
Junya Honda
, Shinji Ito,
Chansoo Kim
Adversarial Learning in Games with Bandit Feedback: Logarithmic Pure-Strategy Maximin Regret
COLT 2026 · Shinji Ito,
Haipeng Luo
,
Arnab Maiti
,
Taira Tsuchiya
,
Yue Wu
Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback
NeurIPS 2025 · Shinji Ito,
Kevin G. Jamieson
,
Haipeng Luo
,
Arnab Maiti
,
Taira Tsuchiya
Bandit Max-Min Fair Allocation
ECML-PKDD 2025 ·
Tsubasa Harada
, Shinji Ito,
Hanna Sumita
Corrupted Learning Dynamics in Games
COLT 2025 ·
Taira Tsuchiya
, Shinji Ito,
Haipeng Luo
Data-dependent Bounds with T-Optimal Best-of-Both-Worlds Guarantees in Multi-Armed Bandits using Stability-Penalty Matching
COLT 2025 ·
Quan M. Nguyen
, Shinji Ito,
Junpei Komiyama
,
Nishant A. Mehta
Instance-Dependent Regret Bounds for Learning Two-Player Zero-Sum Games with Bandit Feedback
COLT 2025 · Shinji Ito,
Haipeng Luo
,
Taira Tsuchiya
,
Yue Wu
LC-Tsallis-INF: Generalized Best-of-Both-Worlds Linear Contextual Bandits
AISTATS 2025 ·
Masahiro Kato
, Shinji Ito
Optimal Dynamic Regret by Transformers for Non-Stationary Reinforcement Learning
NeurIPS 2025 ·
Baiyuan Chen
, Shinji Ito,
Masaaki Imaizumi
Optimal Regret of Bandits under Differential Privacy
NeurIPS 2025 ·
Achraf Azize
,
Yulian Wu
,
Junya Honda
,
Francesco Orabona
, Shinji Ito,
Debabrota Basu
Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems
NeurIPS 2025 ·
Jongyeong Lee
,
Junya Honda
, Shinji Ito,
Min-hwan Oh
A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $\Theta(T{2/3})$ and its Application to Best-of-Both-Worlds
NeurIPS 2024 ·
Taira Tsuchiya
, Shinji Ito
Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds
COLT 2024 · Shinji Ito,
Taira Tsuchiya
,
Junya Honda
Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring
ICML 2024 ·
Taira Tsuchiya
, Shinji Ito,
Junya Honda
Fast Rates in Stochastic Online Convex Optimization by Exploiting the Curvature of Feasible Sets
NeurIPS 2024 ·
Taira Tsuchiya
, Shinji Ito
Follow-the-Perturbed-Leader with Fréchet-type Tail Distributions: Optimality in Adversarial Bandits and Best-of-Both-Worlds
COLT 2024 ·
Jongyeong Lee
,
Junya Honda
, Shinji Ito,
Min-hwan Oh
Learning with Posterior Sampling for Revenue Management under Time-varying Demand
IJCAI 2024 ·
Kazuma Shimizu
,
Junya Honda
, Shinji Ito,
Shinji Nakadai
New Classes of the Greedy-Applicable Arm Feature Distributions in the Sparse Linear Bandit Problem
AAAI 2024 ·
Koji Ichikawa
, Shinji Ito,
Daisuke Hatano
,
Hanna Sumita
,
Takuro Fukunaga
,
Naonori Kakimura
,
Ken-ichi Kawarabayashi
On the Minimax Regret for Contextual Linear Bandits and Multi-Armed Bandits with Expert Advice
NeurIPS 2024 · Shinji Ito
Online $\textrm{L}{\natural }$-Convex Minimization
ECML-PKDD 2024 ·
Ken Yokoyama
, Shinji Ito,
Tatsuya Matsuoka
,
Kei Kimura
,
Makoto Yokoo