0dfd8a39e2a5dd536c185e19a804a73b-Paper.pdf

Despite tremendous success in many application scenarios, the training and inference costs of using deep learning are also rapidly increasing over time. The lottery tickethypothesis (LTH)emergesasapromising frameworktoleverage a special sparse subnetwork (i.e.,winning ticket) instead of a full model for both training and inference, that can lower both costs without sacrificing the performance.