3 citations · 5 across the 3 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Taming Score-Based Denoisers in ADMM: A Convergent Plug-and-Play Framework
Rajesh Shrestha, Xiao Fu
While score-based generative models have emerged as powerful priors for solving inverse problems, directly integrating them into optimization algorithms such as ADMM remains nontri…
cs.LG2023★ 3 cited
Natural Gradient Methods: Perspectives, Efficient-Scalable Approximations, and Analysis
Rajesh Shrestha
Natural Gradient Descent, a second-degree optimization method motivated by the information geometry, makes use of the Fisher Information Matrix instead of the Hessian which is typi…