activity
20122023
most citedA Memory-Efficient Sketch Method for Estimating High Similarities in Streaming Sets

39 citations · 93 across the 27 of their papers we have counts for

collaborators
Showing cs.LGShow all

19 papers · 1 filter

cs.LG2023

Cooperative Multi-agent Bandits: Distributed Algorithms with Optimal Individual Regret and Constant Communication Costs

Lin Yang, Xuchuang Wang, Mohammad Hajiesmaili +3

Recently, there has been extensive study of cooperative multi-agent multi-armed bandits where a set of distributed agents cooperatively play the same multi-armed bandit game. The g…

cs.LG2023

Multi-Fidelity Multi-Armed Bandits Revisited

Xuchuang Wang, Qingyun Wu, Wei Chen +1

We study the multi-fidelity multi-armed bandit (MF-MAB), an extension of the canonical multi-armed bandit (MAB) problem. MF-MAB allows each arm to be pulled with different costs (f…

cs.LG2023

A Survey of Federated Evaluation in Federated Learning

Behnaz Soltani, Yipeng Zhou, Venus Haghighi +1

In traditional machine learning, it is trivial to conduct model evaluation since all data samples are managed centrally by a server. However, model evaluation becomes a challenging…

cs.LG2023

Contextual Combinatorial Bandits with Probabilistically Triggered Arms

Xutong Liu, Jinhang Zuo, Siwei Wang +4

We study contextual combinatorial bandits with probabilistically triggered arms (CMAB-T) under a variety of smoothness conditions that capture a wide range of applications, suc…

cs.LG2023

Uncertainty-Aware Instance Reweighting for Off-Policy Learning

Xiaoying Zhang, Junpu Chen, Hongning Wang +4

Off-policy learning, referring to the procedure of policy optimization with access only to logged feedback data, has shown importance in various real-world applications, such as se…

cs.LG2023

Efficient Explorative Key-term Selection Strategies for Conversational Contextual Bandits

Zhiyong Wang, Xutong Liu, Shuai Li +1

Conversational contextual bandits elicit user preferences by occasionally querying for explicit feedback on key-terms to accelerate learning. However, there are aspects of existing…