Follow
Taira Tsuchiya
Taira Tsuchiya
Verified email at mist.i.u-tokyo.ac.jp - Homepage
Title
Cited by
Cited by
Year
Speaker invariant feature extraction for zero-resource languages with adversarial learning
T Tsuchiya, N Tawara, T Ogawa, T Kobayashi
2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018
362018
Nearly optimal best-of-both-worlds algorithms for online learning with feedback graphs
S Ito, T Tsuchiya, J Honda
Advances in Neural Information Processing Systems (NeurIPS 2022), 2022
222022
Best-of-Both-Worlds Algorithms for Partial Monitoring
T Tsuchiya, S Ito, J Honda
International Conference on Algorithmic Learning Theory (ALT 2023), 1484-1515, 2022
182022
Adversarially robust multi-armed bandit algorithm with variance-dependent regret bounds
S Ito, T Tsuchiya, J Honda
Conference on Learning Theory, 1421-1422, 2022
162022
Minimax Optimal Algorithms for Fixed-Budget Best Arm Identification
J Komiyama, T Tsuchiya, J Honda
Advances in Neural Information Processing Systems (NeurIPS 2022), 2022
162022
Semi-supervised ordinal regression based on empirical risk minimization
T Tsuchiya, N Charoenphakdee, I Sato, M Sugiyama
Neural Computation 33 (12), 3361-3412, 2021
112021
Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring
T Tsuchiya, J Honda, M Sugiyama
Advances in Neural Information Processing Systems 33 (NeurIPS 2020), 8861-8871, 2020
102020
Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds
T Tsuchiya, S Ito, J Honda
Advances in Neural Information Processing Systems (NeurIPS 2023), 2023
62023
Further adaptive best-of-both-worlds algorithm for combinatorial semi-bandits
T Tsuchiya, S Ito, J Honda
International Conference on Artificial Intelligence and Statistics (AISTATS …, 2023
52023
Follow-the-Perturbed-Leader Achieves Best-of-Both-Worlds for Bandit Problems
J Honda, S Ito, T Tsuchiya
International Conference on Algorithmic Learning Theory (ALT 2023), 726-754, 2023
52023
Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Ratio Analysis and Best-of-Both-Worlds
S Ito, T Tsuchiya, J Honda
arXiv preprint arXiv:2403.00715, 2024
2024
Fast Rates in Online Convex Optimization by Exploiting the Curvature of Feasible Sets
T Tsuchiya, S Ito
arXiv preprint arXiv:2402.12868, 2024
2024
Online Control of Linear Systems with Unbounded and Degenerate Noise
K Ito, T Tsuchiya
arXiv preprint arXiv:2402.10252, 2024
2024
Online Structured Prediction with Fenchel--Young Losses and Improved Surrogate Regret for Online Multiclass Classification with Logistic Loss
S Sakaue, H Bao, T Tsuchiya, T Oki
arXiv preprint arXiv:2402.08180, 2024
2024
Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring
T Tsuchiya, S Ito, J Honda
arXiv preprint arXiv:2402.08321, 2024
2024
Best-of-Both-Worlds Algorithms for Linear Contextual Bandits
Y Kuroki, A Rumi, T Tsuchiya, F Vitale, N Cesa-Bianchi
arXiv preprint arXiv:2312.15433, 2023
2023
Environment Adaptive Regret Analysis in Bandit Problems
T Tsuchiya
Kyoto University, 2023
2023
Globally Optimal Algorithms for Fixed-Budget Best Arm Identification
J Komiyama, T Tsuchiya, J Honda
arXiv preprint arXiv:2206.04646, 2022
2022
The system can't perform the operation now. Try again later.
Articles 1–18