Zobrazeno 1 - 10
of 387
pro vyhledávání: '"Liang, Ben"'
Error accumulation is an essential component of the Top-$k$ sparsification method in distributed gradient descent. It implicitly scales the learning rate and prevents the slow-down of lateral movement, but it can also deteriorate convergence. This pa
Externí odkaz:
http://arxiv.org/abs/2409.14893
We propose an uplink over-the-air aggregation (OAA) method for wireless federated learning (FL) that simultaneously trains multiple models. To maximize the multi-model training convergence rate, we derive an upper bound on the optimality gap of the g
Externí odkaz:
http://arxiv.org/abs/2409.00978
Next-generation wireless networks need to handle massive user access effectively. This paper addresses the problem of joint group scheduling and multicast beamforming for downlink transmission with many active user groups. Aiming to maximize the mini
Externí odkaz:
http://arxiv.org/abs/2403.10002
This paper studies the design of wireless federated learning (FL) for simultaneously training multiple machine learning models. We consider round robin device-model assignment and downlink beamforming for concurrent multiple model updates. After form
Externí odkaz:
http://arxiv.org/abs/2312.13424
Knowledge distillation (KD) improves the performance of a low-complexity student model with the help of a more powerful teacher. The teacher in KD is a black-box model, imparting knowledge to the student only through its predictions. This limits the
Externí odkaz:
http://arxiv.org/abs/2310.02572
We study joint downlink-uplink beamforming design for wireless federated learning (FL) with a multi-antenna base station. Considering analog transmission over noisy channels and uplink over-the-air aggregation, we derive the global model update expre
Externí odkaz:
http://arxiv.org/abs/2307.00315
Publikováno v:
2021 IEEE Global Communications Conference (GLOBECOM)
Large datasets in machine learning often contain missing data, which necessitates the imputation of missing data values. In this work, we are motivated by network traffic classification, where traditional data imputation methods do not perform well.
Externí odkaz:
http://arxiv.org/abs/2303.10681
Federated learning (FL) with over-the-air computation can efficiently utilize the communication bandwidth but is susceptible to analog aggregation error. Excluding those devices with weak channel conditions can reduce the aggregation error, but it al
Externí odkaz:
http://arxiv.org/abs/2302.14336
Publikováno v:
IEEE Transactions on Signal Processing, 2023
In this work, we propose ultra-low-complexity design solutions for multi-group multicast beamforming in large-scale systems. For the quality-of-service (QoS) problem, by utilizing the optimal multicast beamforming structure obtained recently in [2],
Externí odkaz:
http://arxiv.org/abs/2206.01846
Autor:
Eshraghi, Nima, Liang, Ben
The performance of online convex optimization algorithms in a dynamic environment is often expressed in terms of the dynamic regret, which measures the decision maker's performance against a sequence of time-varying comparators. In the analysis of th
Externí odkaz:
http://arxiv.org/abs/2202.12843