arXiv subjects

Yusuke Kaneko

Publications and source records attributed to Yusuke Kaneko.

3 recordsLinked to original sources

arXiv2023

Orienting undirected phylogenetic networks to tree-child network

Phylogenetic networks are used to represent the evolutionary history of species. They are versatile when compared to traditional phylogenetic trees, as they capture more complex evolutionary events such as hybridization and horizontal gene transfer. Distance-based methods such as the Neighbor-Net algorithm are widely used to compute phylogenetic networks from data. However, the output is necessarily an undirected graph, posing a great challenge to deduce the direction of genetic flow in order to infer the true evolutionary history. Recently, Huber et al. investigated two different computational problems relevant to orienting undirected phylogenetic networks into directed ones. In this paper, we consider the problem of orienting an undirected binary network into a tree-child network. We give some necessary conditions for determining the tree-child orientability, such as a tight upper bound on the size of tree-child orientable graphs, as well as many interesting examples. In addition, we introduce new families of undirected phylogenetic networks, the jellyfish graphs and ladder graphs, that are orientable but not tree-child orientable. We also prove that any ladder graph can be made tree-child orientable by adding extra leaves, and describe a simple algorithm for orienting a ladder graph to a tree-child network with the minimum number of extra leaves. We pose many open problems as well.

math.CO↗

arXiv2020

Off-Policy Exploitability-Evaluation in Two-Player Zero-Sum Markov Games

Off-policy evaluation (OPE) is the problem of evaluating new policies using historical data obtained from a different policy. In the recent OPE context, most studies have focused on single-player cases, and not on multi-player cases. In this study, we propose OPE estimators constructed by the doubly robust and double reinforcement learning estimators in two-player zero-sum Markov games. The proposed estimators project exploitability that is often used as a metric for determining how close a policy profile (i.e., a tuple of policies) is to a Nash equilibrium in two-player zero-sum games. We prove the exploitability estimation error bounds for the proposed estimators. We then propose the methods to find the best candidate policy profile by selecting the policy profile that minimizes the estimated exploitability from a given policy profile class. We prove the regret bounds of the policy profiles selected by our methods. Finally, we demonstrate the effectiveness and performance of the proposed estimators through experiments.

cs.LG↗

arXiv2020

Off-Policy Evaluation of Bandit Algorithm from Dependent Samples under Batch Update Policy

The goal of off-policy evaluation (OPE) is to evaluate a new policy using historical data obtained via a behavior policy. However, because the contextual bandit algorithm updates the policy based on past observations, the samples are not independent and identically distributed (i.i.d.). This paper tackles this problem by constructing an estimator from a martingale difference sequence (MDS) for the dependent samples. In the data-generating process, we do not assume the convergence of the policy, but the policy uses the same conditional probability of choosing an action during a certain period. Then, we derive an asymptotically normal estimator of the value of an evaluation policy. As another advantage of our method, the batch-based approach simultaneously solves the deficient support problem. Using benchmark and real-world datasets, we experimentally confirm the effectiveness of the proposed method.

cs.LG↗