Picture for Taira Tsuchiya

Taira Tsuchiya

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

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

Add code
Mar 10, 2024
Viaarxiv icon

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

Add code
Feb 20, 2024
Viaarxiv icon

Online Control of Linear Systems with Unbounded and Degenerate Noise

Add code
Feb 15, 2024
Viaarxiv icon

Online Structured Prediction with Fenchel--Young Losses and Improved Surrogate Regret for Online Multiclass Classification with Logistic Loss

Add code
Feb 13, 2024
Viaarxiv icon

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

Add code
Feb 13, 2024
Viaarxiv icon

Best-of-Both-Worlds Algorithms for Linear Contextual Bandits

Add code
Dec 24, 2023
Viaarxiv icon

Stability-penalty-adaptive Follow-the-regularized-leader: Sparsity, Game-dependency, and Best-of-both-worlds

Add code
May 26, 2023
Viaarxiv icon

Best-of-Both-Worlds Algorithms for Partial Monitoring

Add code
Jul 29, 2022
Figure 1 for Best-of-Both-Worlds Algorithms for Partial Monitoring
Viaarxiv icon

Adversarially Robust Multi-Armed Bandit Algorithm with Variance-Dependent Regret Bounds

Add code
Jun 14, 2022
Figure 1 for Adversarially Robust Multi-Armed Bandit Algorithm with Variance-Dependent Regret Bounds
Figure 2 for Adversarially Robust Multi-Armed Bandit Algorithm with Variance-Dependent Regret Bounds
Figure 3 for Adversarially Robust Multi-Armed Bandit Algorithm with Variance-Dependent Regret Bounds
Figure 4 for Adversarially Robust Multi-Armed Bandit Algorithm with Variance-Dependent Regret Bounds
Viaarxiv icon