IEEE INFOCOM 2022
Distributed Bandits with Heterogeneous Agents
Lin Yang (University of Massachusetts, Amherst, USA); Yu-Zhen Janice Chen (University of Massachusetts at Amherst, USA); Mohammad Hajiesmaili (University of Massachusetts Amherst, USA); John Chi Shing Lui (Chinese University of Hong Kong, Hong Kong); Don Towsley (University of Massachusetts at Amherst, USA)
The goal for each agent is to find its optimal local arm and agents are able to cooperate by sharing their observations. For this heterogeneous multi-agent setting, we propose two respective algorithms, CO-UCB and CO-AAE.
Both algorithms are proven to attain the order-optimal regret, .., where .. is the minimum suboptimality gap between the reward mean of arm .. and any local optimal arm. In addition, a careful selection of the valuable information for cooperation, CO-AAE achieves a low communication complexity. Last, numerical experiments verifies the efficiency of both algorithms.
Experimental Design Networks: A Paradigm for Serving Heterogeneous Learners under Networking Constraints
Yuezhou Liu, Yuanyuan Li, Lili Su, Edmund Yeh and Stratis Ioannidis (Northeastern University, USA)
In this paper, we propose an experimental design network paradigm, wherein learner nodes train possibly different Bayesian linear regression models via consuming data streams generated by data source nodes over a network. We formulate this problem as a social welfare optimization problem in which the global objective is defined as the sum of experimental design objectives of individual learners, and the decision variables are the data transmission strategies subject to network constraints. We first show that, assuming Poisson data streams, the global objective is a continuous DR-submodular function. We then propose a Frank-Wolfe type algorithm that outputs a solution within a 1-1/e factor from the optimal. Our algorithm contains a novel gradient estimation component which is carefully designed based on Poisson tail bounds and sampling. Finally, we complement our theoretical findings through extensive experiments. Our numerical evaluation shows that the proposed algorithm outperforms several baseline algorithms both in maximizing the global objective and in the quality of the trained models.
MC-Sketch: Enabling Heterogeneous Network Monitoring Resolutions with Multi-Class Sketch
Kate Ching-Ju Lin (National Chiao Tung University, Taiwan); Wei-Lun Lai (National Yang-Ming Chiao Tung University, Taiwan)
Stream Iterative Distributed Coded Computing for Learning Applications in Heterogeneous Systems
Homa Esfahanizadeh (Massachusetts Institute of Technology, USA); Alejandro Cohen (Technion, Israel); Muriel Médard (MIT, USA)
Jun Li (City University of New York)
E2E Fidelity Aware Routing and Purification for Throughput Maximization in Quantum Networks
Yangming Zhao and Gongming Zhao (University of Science and Technology of China, China); Chunming Qiao (University at Buffalo, USA)
This work represents the first attempt to formulate the E2E fidelity of an entanglement connection consisting of multiple entanglement links, and use this E2E fidelity to determine critical links for the most cost-effective purification. A novel approach called E2E Fidelity aware Routing and Purification (EFiRAP) is proposed to maximize the network throughput, i.e., the number of entanglement connections among multiple SD pairs, each having a fidelity above a given threshold. EFiRAP first prepares multiple candidate entanglement paths and corresponding purification schemes, and then selects the final set of entanglement paths that can maximize network throughput under the quantum resource constraints. EFiRAP is the first-of-its-kind that ensures that the E2E fidelity of all the established entanglement connections rather than only the individual links is above a given threshold. Extensive simulations show that EFiRAP can enhance the network throughput by up to 54.03% compared with the state-of-the-art technique.
Opportunistic Routing in Quantum Networks
Ali Farahbakhsh and Chen Feng (University of British Columbia, Canada)
Optimal Routing for Stream Learning Systems
Xinzhe Fu (Massachusetts Institute of Technology, USA); Eytan Modiano (MIT, USA)
Multi-Entanglement Routing Design over Quantum Networks
Yiming Zeng, Jiarui Zhang, Ji Liu, Zhenhua Liu and Yuanyuan Yang (Stony Brook University, USA)
Jianqing Liu (University of Alabama in Huntsville)