Artificial intelligence (AI) has achieved remarkable breakthroughs in a wide range of fields, ranging from speech processing, image classification to drug discovery. This is driven by the …
The growing energy and performance costs of deep learning have driven the community to reduce the size of neural networks by selectively pruning components. Similarly to their …
Federated learning (FL) enables edge devices, such as Internet of Things devices (eg, sensors), servers, and institutions (eg, hospitals), to collaboratively train a machine learning …
Distributed training of foundation models, especially large language models (LLMs), is communication-intensive and so has heavily relied on centralized data centers with fast …
MM Amiri, D Gündüz - IEEE Transactions on Wireless …, 2020 - ieeexplore.ieee.org
We study federated machine learning at the wireless network edge, where limited power wireless devices, each with its own dataset, build a joint model with the help of a remote …
In federated learning, communication cost is often a critical bottleneck to scale up distributed optimization algorithms to collaboratively learn a model from millions of devices with …
We consider a distributed empirical risk minimization (ERM) optimization problem with communication efficiency and privacy requirements, motivated by the federated learning …
Huge scale machine learning problems are nowadays tackled by distributed optimization algorithms, ie algorithms that leverage the compute power of many devices for training. The …
Y Jiang, S Wang, V Valls, BJ Ko… - … on Neural Networks …, 2022 - ieeexplore.ieee.org
Federated learning (FL) allows model training from local data collected by edge/mobile devices while preserving data privacy, which has wide applicability to image and vision …