18 citations · 66 across the 10 of their papers we have counts for
10 papers
Importance Weighting Approach in Kernel Bayes' Rule
Liyuan Xu, Yutian Chen, Arnaud Doucet +1
We study a nonparametric approach to Bayesian computation via feature means, where the expectation of prior features is updated to yield expected kernel posterior features, based o…
Deep Proxy Causal Learning and its Application to Confounded Bandit Policy Evaluation
Liyuan Xu, Heishiro Kanagawa, Arthur Gretton
Proxy causal learning (PCL) is a method for estimating the causal effect of treatments on outcomes in the presence of unobserved confounding, using proxies (structured side informa…
On Instrumental Variable Regression for Deep Offline Policy Evaluation
Yutian Chen, Liyuan Xu, Caglar Gulcehre +4
We show that the popular reinforcement learning (RL) strategy of estimating the state-action value (Q-function) by minimizing the mean squared Bellman error leads to a regression p…
Learning Deep Features in Instrumental Variable Regression
Liyuan Xu, Yutian Chen, Siddarth Srinivasan +3
Instrumental variable (IV) regression is a standard strategy for learning causal relationships between confounded treatment and outcome variables from observational data by utilizi…
Pairwise Supervision Can Provably Elicit a Decision Boundary
Han Bao, Takuya Shimada, Liyuan Xu +2
Similarity learning is a general problem to elicit useful representations by predicting the relationship between a pair of patterns. This problem is related to various important pr…
Uncoupled Regression from Pairwise Comparison Data
Liyuan Xu, Junya Honda, Gang Niu +1
Uncoupled regression is the problem to learn a model from unlabeled data and the set of target values while the correspondence between them is unknown. Such a situation arises in p…
Polynomial-time Algorithms for Multiple-arm Identification with Full-bandit Feedback
Yuko Kuroki, Liyuan Xu, Atsushi Miyauchi +2
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 supe…
Dueling Bandits with Qualitative Feedback
Liyuan Xu, Junya Honda, Masashi Sugiyama
We formulate and study a novel multi-armed bandit problem called the qualitative dueling bandit (QDB) problem, where an agent observes not numeric but qualitative feedback by pulli…
Alternate Estimation of a Classifier and the Class-Prior from Positive and Unlabeled Data
Masahiro Kato, Liyuan Xu, Gang Niu +1
We consider a problem of learning a binary classifier only from positive data and unlabeled data (PU learning) and estimating the class-prior in unlabeled data under the case-contr…
Fully adaptive algorithm for pure exploration in linear bandits
Liyuan Xu, Junya Honda, Masashi Sugiyama
We propose the first fully-adaptive algorithm for pure exploration in linear bandits---the task to find the arm with the largest expected reward, which depends on an unknown parame…