Junya Honda
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Junya Honda has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Akimichi Takemura
Shiga University
5 shared publications - Hiroshi Nakagawa
Junya Honda The University of Tokyo Japan
2 shared publications - Atsushi Miyauchi
CENTAI Institute, Turin, Italy
1 shared publication - Hisashi Kashima
Kyoto University, Kyoto, Japan
1 shared publication Junpei Komiyama
The University of Tokyo The University of Tokyo Kyoto University The University of Tokyo
1 shared publication- Junpei Komiyama
Stern School of Business New York University
1 shared publication
Latest Publications
- Open Access
Polynomial-time Algorithms for Multiple-arm Identification with Full-bandit Feedback
We study the problem of stochastic combinatorial pure exploration (CPE), where an agent sequentially pulls a set of single arms (a.k.a. a super arm) and tries to find the best super arm. Among a variety of problem settings of the CPE, we focus on the full-bandit setting, where we cannot observe the reward of each single arm, but only the sum of the rewards. Although we can regard the CPE with full-bandit feedback as a special case of pure exploration in linear bandits, an approach based on linear bandits is not computationally feasible since the number of super arms may be exponential. In this paper, we first propose a polynomial-time bandit algorithm for the CPE under general combinatorial constraints and provide an upper bound of the sample complexity. Second, we design an approximation algorithm for the 0-1 quadratic maximization problem, which arises in many bandit algorithms with confidence ellipsoids. Based on our approximation algorithm, we propose novel bandit algorithms for the top-k selection problem, and prove that our algorithms run in polynomial time. Finally, we conduct experiments on synthetic and real-world datasets, and confirm the validity of our theoretical analysis in terms of both the computation time and the sample complexity.
Open AccessPolynomial-time Algorithms for Multiple-arm Identification with Full-bandit Feedback
We study the problem of stochastic combinatorial pure exploration (CPE), where an agent sequentially pulls a set of single arms (a.k.a. a super arm) and tries to find the best super arm. Among a variety of problem settings of the CPE, we focus on the full-bandit setting, where we cannot observe the reward of each single arm, but only the sum of the rewards. Although we can regard the CPE with full-bandit feedback as a special case of pure exploration in linear bandits, an approach based on linear bandits is not computationally feasible since the number of super arms may be exponential. In this paper, we first propose a polynomial-time bandit algorithm for the CPE under general combinatorial constraints and provide an upper bound of the sample complexity. Second, we design an approximation algorithm for the 0-1 quadratic maximization problem, which arises in many bandit algorithms with confidence ellipsoids. Based on our approximation algorithm, we propose novel bandit algorithms for the top-k selection problem, and prove that our algorithms run in polynomial time. Finally, we conduct experiments on synthetic and real-world datasets, and confirm the validity of our theoretical analysis in terms of both the computation time and the sample complexity.
- Open Access
A Note on KL-UCB+ Policy for the Stochastic Bandit
A classic setting of the stochastic K-armed bandit problem is considered in this note. In this problem it has been known that KL-UCB policy achieves the asymptotically optimal regret bound and KL-UCB+ policy empirically performs better than the KL-UCB policy although the regret bound for the original form of the KL-UCB+ policy has been unknown. This note demonstrates that a simple proof of the asymptotic optimality of the KL-UCB+ policy can be given by the same technique as those used for analyses of other known policies.
Open AccessA Note on KL-UCB+ Policy for the Stochastic Bandit
A classic setting of the stochastic K-armed bandit problem is considered in this note. In this problem it has been known that KL-UCB policy achieves the asymptotically optimal regret bound and KL-UCB+ policy empirically performs better than the KL-UCB policy although the regret bound for the original form of the KL-UCB+ policy has been unknown. This note demonstrates that a simple proof of the asymptotic optimality of the KL-UCB+ policy can be given by the same technique as those used for analyses of other known policies.
- Open Access
Regret Lower Bound and Optimal Algorithm in Finite Stochastic Partial Monitoring
Partial monitoring is a general model for sequential learning with limited feedback formalized as a game between two players. In this game, the learner chooses an action and at the same time the opponent chooses an outcome, then the learner suffers a loss and receives a feedback signal. The goal of the learner is to minimize the total loss. In this paper, we study partial monitoring with finite actions and stochastic outcomes. We derive a logarithmic distribution-dependent regret lower bound that defines the hardness of the problem. Inspired by the DMED algorithm (Honda and Takemura, 2010) for the multi-armed bandit problem, we propose PM-DMED, an algorithm that minimizes the distribution-dependent regret. PM-DMED significantly outperforms state-of-the-art algorithms in numerical experiments. To show the optimality of PM-DMED with respect to the regret bound, we slightly modify the algorithm by introducing a hinge function (PM-DMED-Hinge). Then, we derive an asymptotically optimal regret upper bound of PM-DMED-Hinge that matches the lower bound.
Open AccessRegret Lower Bound and Optimal Algorithm in Finite Stochastic Partial Monitoring
Partial monitoring is a general model for sequential learning with limited feedback formalized as a game between two players. In this game, the learner chooses an action and at the same time the opponent chooses an outcome, then the learner suffers a loss and receives a feedback signal. The goal of the learner is to minimize the total loss. In this paper, we study partial monitoring with finite actions and stochastic outcomes. We derive a logarithmic distribution-dependent regret lower bound that defines the hardness of the problem. Inspired by the DMED algorithm (Honda and Takemura, 2010) for the multi-armed bandit problem, we propose PM-DMED, an algorithm that minimizes the distribution-dependent regret. PM-DMED significantly outperforms state-of-the-art algorithms in numerical experiments. To show the optimality of PM-DMED with respect to the regret bound, we slightly modify the algorithm by introducing a hinge function (PM-DMED-Hinge). Then, we derive an asymptotically optimal regret upper bound of PM-DMED-Hinge that matches the lower bound.
- Open Access
Regret Lower Bound and Optimal Algorithm in Dueling Bandit Problem
We study the $K$-armed dueling bandit problem, a variation of the standard stochastic bandit problem where the feedback is limited to relative comparisons of a pair of arms. We introduce a tight asymptotic regret lower bound that is based on the information divergence. An algorithm that is inspired by the Deterministic Minimum Empirical Divergence algorithm (Honda and Takemura, 2010) is proposed, and its regret is analyzed. The proposed algorithm is found to be the first one with a regret upper bound that matches the lower bound. Experimental comparisons of dueling bandit algorithms show that the proposed algorithm significantly outperforms existing ones.
Open AccessRegret Lower Bound and Optimal Algorithm in Dueling Bandit Problem
We study the $K$-armed dueling bandit problem, a variation of the standard stochastic bandit problem where the feedback is limited to relative comparisons of a pair of arms. We introduce a tight asymptotic regret lower bound that is based on the information divergence. An algorithm that is inspired by the Deterministic Minimum Empirical Divergence algorithm (Honda and Takemura, 2010) is proposed, and its regret is analyzed. The proposed algorithm is found to be the first one with a regret upper bound that matches the lower bound. Experimental comparisons of dueling bandit algorithms show that the proposed algorithm significantly outperforms existing ones.
- Open Access
Optimality of Thompson Sampling for Gaussian Bandits Depends on Priors
In stochastic bandit problems, a Bayesian policy called Thompson sampling (TS) has recently attracted much attention for its excellent empirical performance. However, the theoretical analysis of this policy is difficult and its asymptotic optimality is only proved for one-parameter models. In this paper we discuss the optimality of TS for the model of normal distributions with unknown means and variances as one of the most fundamental example of multiparameter models. First we prove that the expected regret of TS with the uniform prior achieves the theoretical bound, which is the first result to show that the asymptotic bound is achievable for the normal distribution model. Next we prove that TS with Jeffreys prior and reference prior cannot achieve the theoretical bound. Therefore the choice of priors is important for TS and non-informative priors are sometimes risky in cases of multiparameter models.
Open AccessOptimality of Thompson Sampling for Gaussian Bandits Depends on Priors
In stochastic bandit problems, a Bayesian policy called Thompson sampling (TS) has recently attracted much attention for its excellent empirical performance. However, the theoretical analysis of this policy is difficult and its asymptotic optimality is only proved for one-parameter models. In this paper we discuss the optimality of TS for the model of normal distributions with unknown means and variances as one of the most fundamental example of multiparameter models. First we prove that the expected regret of TS with the uniform prior achieves the theoretical bound, which is the first result to show that the asymptotic bound is achievable for the normal distribution model. Next we prove that TS with Jeffreys prior and reference prior cannot achieve the theoretical bound. Therefore the choice of priors is important for TS and non-informative priors are sometimes risky in cases of multiparameter models.
- Open Access
Finite-time Regret Bound of a Bandit Algorithm for the Semi-bounded Support Model
In this paper we consider stochastic multiarmed bandit problems. Recently a policy, DMED, is proposed and proved to achieve the asymptotic bound for the model that each reward distribution is supported in a known bounded interval, e.g. [0,1]. However, the derived regret bound is described in an asymptotic form and the performance in finite time has been unknown. We inspect this policy and derive a finite-time regret bound by refining large deviation probabilities to a simple finite form. Further, this observation reveals that the assumption on the lower-boundedness of the support is not essential and can be replaced with a weaker one, the existence of the moment generating function.
Open AccessFinite-time Regret Bound of a Bandit Algorithm for the Semi-bounded Support Model
In this paper we consider stochastic multiarmed bandit problems. Recently a policy, DMED, is proposed and proved to achieve the asymptotic bound for the model that each reward distribution is supported in a known bounded interval, e.g. [0,1]. However, the derived regret bound is described in an asymptotic form and the performance in finite time has been unknown. We inspect this policy and derive a finite-time regret bound by refining large deviation probabilities to a simple finite form. Further, this observation reveals that the assumption on the lower-boundedness of the support is not essential and can be replaced with a weaker one, the existence of the moment generating function.
- 2 July 2011
- Published by Springer Nature in Machine Learning
- Vol. 85 (3) , 361-391
An asymptotically optimal policy for finite support models in the multiarmed bandit problem
- 2 July 2011
- Published by Springer Nature in Machine Learning
- Vol. 85 (3) , 361-391
An asymptotically optimal policy for finite support models in the multiarmed bandit problem
- Open Access
Stochastic Bandit Based on Empirical Moments
In the multiarmed bandit problem a gambler chooses an arm of a slot machine to pull considering a tradeoff between exploration and exploitation. We study the stochastic bandit problem where each arm has a reward distribution supported in a known bounded interval, e.g. [0,1]. For this model, policies which take into account the empirical variances (i.e. second moments) of the arms are known to perform effectively. In this paper, we generalize this idea and we propose a policy which exploits the first d empirical moments for arbitrary d fixed in advance. The asymptotic upper bound of the regret of the policy approaches the theoretical bound by Burnetas and Katehakis as d increases. By choosing appropriate d, the proposed policy realizes a tradeoff between the computational complexity and the expected regret.
Open AccessStochastic Bandit Based on Empirical Moments
In the multiarmed bandit problem a gambler chooses an arm of a slot machine to pull considering a tradeoff between exploration and exploitation. We study the stochastic bandit problem where each arm has a reward distribution supported in a known bounded interval, e.g. [0,1]. For this model, policies which take into account the empirical variances (i.e. second moments) of the arms are known to perform effectively. In this paper, we generalize this idea and we propose a policy which exploits the first d empirical moments for arbitrary d fixed in advance. The asymptotic upper bound of the regret of the policy approaches the theoretical bound by Burnetas and Katehakis as d increases. By choosing appropriate d, the proposed policy realizes a tradeoff between the computational complexity and the expected regret.
- Open Access
An Asymptotically Optimal Policy for Finite Support Models in the Multiarmed Bandit Problem
We propose minimum empirical divergence (MED) policy for the multiarmed bandit problem. We prove asymptotic optimality of the proposed policy for the case of finite support models. In our setting, Burnetas and Katehakis has already proposed an asymptotically optimal policy. For choosing an arm our policy uses a criterion which is dual to the quantity used in Burnetas and Katehakis. Our criterion is easily computed by a convex optimization technique and has an advantage in practical implementation. We confirm by simulations that MED policy demonstrates good performance in finite time in comparison to other currently popular policies.
Open AccessAn Asymptotically Optimal Policy for Finite Support Models in the Multiarmed Bandit Problem
We propose minimum empirical divergence (MED) policy for the multiarmed bandit problem. We prove asymptotic optimality of the proposed policy for the case of finite support models. In our setting, Burnetas and Katehakis has already proposed an asymptotically optimal policy. For choosing an arm our policy uses a criterion which is dual to the quantity used in Burnetas and Katehakis. Our criterion is easily computed by a convex optimization technique and has an advantage in practical implementation. We confirm by simulations that MED policy demonstrates good performance in finite time in comparison to other currently popular policies.