Researcher profile
Tadashi Wadayama
2 papers in the PaperMetrix corpus
Publications
Papers by this author
-
Theoretical Interpretation of Learned Step Size in Deep-Unfolded Gradient Descent
2020 · arXiv (Cornell University)
Deep unfolding is a promising deep-learning technique in which an iterative algorithm is unrolled to a deep network architecture with trainable parameters. In the case of gradient descent algorithms, as a result of the training …
-
Deep Unfolding-based Weighted Averaging for Federated Learning in Heterogeneous Environments
2022 · arXiv (Cornell University)
Federated learning is a collaborative model training method that iterates model updates by multiple clients and aggregation of the updates by a central server. Device and statistical heterogeneity of participating clients cause significant performance degradation …