7 papers
Adaptive Learning Rates with Surrogate Probability for Follow-the-Perturbed-Leader
Jongyeong Lee, Junya Honda, Shinji Ito +1
Follow-the-regularized-leader framework has shown effectiveness and flexibility in online learning problems, where the choice of learning rates are known to be crucial. Recently, a…
Rate-optimal Design for Anytime Best Arm Identification
Junpei Komiyama, Kyoungseok Jang, Junya Honda
We consider the best arm identification problem, where the goal is to identify the arm with the highest mean reward from a set of arms under a limited sampling budget. This pro…
A Further Efficient Algorithm with Best-of-Both-Worlds Guarantees for -Set Semi-Bandit Problem
Botao Chen, Jongyeong Lee, Chansoo Kim +1
This paper studies the optimality and complexity of Follow-the-Perturbed-Leader (FTPL) policy in -set semi-bandit problems. FTPL has been studied extensively as a promising cand…
Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems
Jongyeong Lee, Junya Honda, Shinji Ito +1
Follow-the-Regularized-Leader (FTRL) policies have achieved Best-of-Both-Worlds (BOBW) results in various settings through hybrid regularizers, whereas analogous results for Follow…
Note on Follow-the-Perturbed-Leader in Combinatorial Semi-Bandit Problems
Botao Chen, Junya Honda
This paper studies the optimality and complexity of Follow-the-Perturbed-Leader (FTPL) policy in size-invariant combinatorial semi-bandit problems. Recently, Honda et al. (2023) an…
Optimal Regret of Bernoulli Bandits under Global Differential Privacy
Achraf Azize, Yulian Wu, Junya Honda +3
As sequential learning algorithms are increasingly applied to real life, ensuring data privacy while maintaining their utilities emerges as a timely question. In this context, regr…