1 code implementation • 9 Jun 2022 • Junpei Komiyama, Taira Tsuchiya, Junya Honda
We introduce two rates, $R^{\mathrm{go}}$ and $R^{\mathrm{go}}_{\infty}$, corresponding to lower bounds on the probability of misidentification, each of which is associated with a proposed algorithm.
no code implementations • 31 Jan 2019 • Taira Tsuchiya, Nontawat Charoenphakdee, Issei Sato, Masashi Sugiyama
We further provide an estimation error bound to show that our risk estimator is consistent.
no code implementations • NeurIPS 2020 • Taira Tsuchiya, Junya Honda, Masashi Sugiyama
We investigate finite stochastic partial monitoring, which is a general model for sequential learning with limited feedback.
no code implementations • 2 Jun 2022 • Shinji Ito, Taira Tsuchiya, Junya Honda
As Alon et al. [2015] have shown, tight regret bounds depend on the structure of the feedback graph: strongly observable graphs yield minimax regret of $\tilde{\Theta}( \alpha^{1/2} T^{1/2} )$, while weakly observable graphs induce minimax regret of $\tilde{\Theta}( \delta^{1/3} T^{2/3} )$, where $\alpha$ and $\delta$, respectively, represent the independence number of the graph and the domination number of a certain portion of the graph.
no code implementations • 14 Jun 2022 • Shinji Ito, Taira Tsuchiya, Junya Honda
In fact, they have provided a stochastic MAB algorithm with gap-variance-dependent regret bounds of $O(\sum_{i: \Delta_i>0} (\frac{\sigma_i^2}{\Delta_i} + 1) \log T )$ for loss variance $\sigma_i^2$ of arm $i$.
no code implementations • 29 Jul 2022 • Taira Tsuchiya, Shinji Ito, Junya Honda
This study considers the partial monitoring problem with $k$-actions and $d$-outcomes and provides the first best-of-both-worlds algorithms, whose regrets are favorably bounded both in the stochastic and adversarial regimes.
no code implementations • NeurIPS 2023 • Taira Tsuchiya, Shinji Ito, Junya Honda
With this result, we establish several algorithms with three types of adaptivity: sparsity, game-dependency, and best-of-both-worlds (BOBW).
no code implementations • 24 Dec 2023 • Yuko Kuroki, Alberto Rumi, Taira Tsuchiya, Fabio Vitale, Nicolò Cesa-Bianchi
We study best-of-both-worlds algorithms for $K$-armed linear contextual bandits.
no code implementations • 13 Feb 2024 • Taira Tsuchiya, Shinji Ito, Junya Honda
This development allows us to significantly improve the existing regret bounds of best-of-both-worlds (BOBW) algorithms, which achieves nearly optimal bounds both in stochastic and adversarial environments.
no code implementations • 13 Feb 2024 • Shinsaku Sakaue, Han Bao, Taira Tsuchiya, Taihei Oki
We extend the exploit-the-surrogate-gap framework to online structured prediction with \emph{Fenchel--Young losses}, a large family of surrogate losses including the logistic loss for multiclass classification, obtaining finite surrogate regret bounds in various structured prediction problems.
no code implementations • 15 Feb 2024 • Kaito Ito, Taira Tsuchiya
Moreover, when the costs are strongly convex, we establish an $ O({\rm poly} (\log T)) $ regret bound without the assumption that noise covariance is non-degenerate, which has been required in the literature.
no code implementations • 20 Feb 2024 • Taira Tsuchiya, Shinji Ito
We first prove that if an optimal decision is on the boundary of a feasible set and the gradient of an underlying loss function is non-zero, then the algorithm achieves a regret upper bound of $O(\rho \log T)$ in stochastic environments.
no code implementations • 1 Mar 2024 • Shinji Ito, Taira Tsuchiya, Junya Honda
Follow-The-Regularized-Leader (FTRL) is known as an effective and versatile approach in online learning, where appropriate choice of the learning rate is crucial for smaller regret.