activity
20162020
most citedIncentivized Exploration for Multi-Armed Bandits under Reward Drift

1 citations · 1 across the 4 of their papers we have counts for

collaborators

10 papers

cs.LG2020

A Smoothed Analysis of Online Lasso for the Sparse Linear Contextual Bandit Problem

Zhiyuan Liu, Huazheng Wang, Bo Waggoner +3

We investigate the sparse linear contextual bandit problem where the parameter is sparse. To relieve the sampling inefficiency, we utilize the "perturbed adversary" where the c…

math.OC2020

Multi-Level Optimal Power Flow Solver in Large Distribution Networks

Xinyang Zhou, Yue Chen, Zhiyuan Liu +2

Solving optimal power flow (OPF) problems for large distribution networks incurs high computational complexity. We consider a large multi-phase distribution network of tree topolog…

cs.HC2019

Utilizing Players' Playtime Records for Churn Prediction: Mining Playtime Regularity

Wanshan Yang, Ting Huang, Junlin Zeng +4

In the free online game industry, churn prediction is an important research topic. Reducing the churn rate of a game significantly helps with the success of the game. Churn predict…

cs.LG20191 cited

Incentivized Exploration for Multi-Armed Bandits under Reward Drift

Zhiyuan Liu, Huazheng Wang, Fan Shen +2

We study incentivized exploration for the multi-armed bandit (MAB) problem where the players receive compensation for exploring arms other than the greedy choice and may provide bi…

eess.SP2019

Towards Scalable Koopman Operator Learning: Convergence Rates and A Distributed Learning Algorithm

Zhiyuan Liu, Guohui Ding, Lijun Chen +1

We propose an alternating optimization algorithm to the nonconvex Koopman operator learning problem for nonlinear dynamic systems. We show that the proposed algorithm will converge…

math.OC2019

Solving Optimal Power Flow for Distribution Networks with State Estimation Feedback

Yi Guo, Xinyang Zhou, Changhong Zhao +3

Conventional optimal power flow (OPF) solvers assume full observability of the involved system states. However, in practice, there is a lack of reliable system monitoring devices i…