伊藤 伸志

Active model selection: A variance minimization approach 

Machine Learning 2024年11月21日  査読有り

Online $\textrm{L}^{\natural }$-Convex Minimization. 

Machine Learning and Knowledge Discovery in Databases. Research Track - European Conference 319-336 2024年  査読有り

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

NeurIPS 2024年  査読有り

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年  査読有り

On the Minimax Regret for Contextual Linear Bandits and Multi-Armed Bandits with Expert Advice. 

NeurIPS 2024年  査読有り筆頭著者責任著者

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

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence(IJCAI) 4911-4919 2024年  査読有り

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

Forty-first International Conference on Machine Learning(ICML) 2024年  査読有り

Best-of-Both-Worlds Linear Contextual Bandits. 

Transactions on Machine Learning Research 2024 2024年  査読有り

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

COLT 3375-3430 2024年  査読有り

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

COLT 2522-2563 2024年  査読有り筆頭著者責任著者

New Classes of the Greedy-Applicable Arm Feature Distributions in the Sparse Linear Bandit Problem. 

AAAI 12708-12716 2024年  査読有り

Maximization of Minimum Weighted Hamming Distance between Set Pairs. 

Asian Conference on Machine Learning(ACML) 895-910 2023年  査読有り

Best-of-Three-Worlds Linear Bandit Algorithm with Variance-Adaptive Regret Bounds. 

COLT 2653-2677 2023年  査読有り筆頭著者責任著者

An Exploration-by-Optimization Approach to Best of Both Worlds in Linear Bandits 

NeurIPS 2023年  査読有り筆頭著者責任著者

Bandit Task Assignment with Unknown Processing Time 

NeurIPS 2023年  査読有り筆頭著者責任著者

Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds 

NeurIPS 2023年  査読有り

Further Adaptive Best-of-Both-Worlds Algorithm for Combinatorial Semi-Bandits. 

AISTATS 8117-8144 2023年  査読有り

Best-of-Three-Worlds Linear Bandit Algorithm with Variance-Adaptive Regret Bounds. 

Conference on Learning Theory (COLT) 2653-2677 2023年  査読有り筆頭著者責任著者

Best-of-Both-Worlds Algorithms for Partial Monitoring. 

ALT 1484-1515 2023年  査読有り