An LSTM-based model predicts coordinate-wise step sizes for BFGS and reports faster convergence while claiming theoretical guarantees that are only partially met.
A Class of Methods for Solving Nonlinear Simultaneous Equations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Learn-to-Optimize Approach for Coordinate-Wise Step Sizes for Quasi-Newton Methods
An LSTM-based model predicts coordinate-wise step sizes for BFGS and reports faster convergence while claiming theoretical guarantees that are only partially met.