9 citations · 25 across the 13 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2020★ 3 cited
Convergence Acceleration via Chebyshev Step: Plausible Interpretation of Deep-Unfolded Gradient Descent
Satoshi Takabe, Tadashi Wadayama
Deep unfolding is a promising deep-learning technique, whose network architecture is based on expanding the recursive structure of existing iterative algorithms. Although convergen…
cs.LG2020★ 9 cited
Theoretical Interpretation of Learned Step Size in Deep-Unfolded Gradient Descent
Satoshi Takabe, Tadashi Wadayama
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…