Picture for Shinji Ito

Shinji Ito

A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $Θ$ and its Application to Best-of-Both-Worlds

Add code
May 30, 2024
Viaarxiv icon

Learning with Posterior Sampling for Revenue Management under Time-varying Demand

Add code
May 08, 2024
Viaarxiv icon

Online $\mathrm{L}^{ atural}$-Convex Minimization

Add code
Apr 26, 2024
Viaarxiv icon

Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds

Add code
Mar 10, 2024
Viaarxiv icon

Follow-the-Perturbed-Leader with Fréchet-type Tail Distributions: Optimality in Adversarial Bandits and Best-of-Both-Worlds

Add code
Mar 08, 2024
Viaarxiv icon

LC-Tsalis-INF: Generalized Best-of-Both-Worlds Linear Contextual Bandits

Add code
Mar 05, 2024
Viaarxiv icon

Fast Rates in Online Convex Optimization by Exploiting the Curvature of Feasible Sets

Add code
Feb 20, 2024
Viaarxiv icon

Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring

Add code
Feb 13, 2024
Viaarxiv icon

Replicability is Asymptotically Free in Multi-armed Bandits

Add code
Feb 12, 2024
Viaarxiv icon

Best-of-Both-Worlds Linear Contextual Bandits

Add code
Dec 27, 2023
Figure 1 for Best-of-Both-Worlds Linear Contextual Bandits
Viaarxiv icon