Search Results for author:
Found 3 papers, 0 papers with code
ZiCo-BC: A Bias Corrected Zero-Shot NAS for Vision Tasks
To solve the problem, we propose a novel bias correction on ZiCo, called ZiCo-BC.
Inference Latency Prediction at the Edge
With the growing workload of inference tasks on mobile devices, state-of-the-art neural architectures (NAs) are typically designed through Neural Architecture Search (NAS) to identify NAs with good tradeoffs between accuracy and efficiency (e. g., latency).
Throughput Prediction of Asynchronous SGD in TensorFlow
Our approach is able to model the interaction of multiple nodes and the scheduling of concurrent transmissions between the parameter server and each node.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
