Statements (30)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
mathematical optimization
|
| gptkbp:advantage |
low memory requirement
may converge slowly for ill-conditioned problems |
| gptkbp:category |
numerical analysis
mathematical optimization |
| gptkbp:developedBy |
gptkb:Jorge_Nocedal
gptkb:Dong_C._Liu |
| gptkbp:estimatedCost |
inverse Hessian matrix
|
| gptkbp:firstPublished |
1989
|
| gptkbp:fullName |
gptkb:Limited-memory_Broyden–Fletcher–Goldfarb–Shanno_algorithm
|
| https://www.w3.org/2000/01/rdf-schema#label |
L-BFGS
|
| gptkbp:input |
objective function
gradient |
| gptkbp:memoryUsage |
limited
|
| gptkbp:output |
local minimum
|
| gptkbp:relatedTo |
gptkb:BFGS_algorithm
|
| gptkbp:supportsAlgorithm |
gptkb:quasi-Newton_method
|
| gptkbp:usedFor |
gptkb:machine_learning
logistic regression training neural networks large-scale optimization numerical optimization |
| gptkbp:usedIn |
gptkb:TensorFlow
gptkb:PyTorch gptkb:scipy.optimize |
| gptkbp:bfsParent |
gptkb:BFGS
gptkb:L-BFGS-B gptkb:Optimization_for_Machine_Learning gptkb:Conditional_Random_Field |
| gptkbp:bfsLayer |
7
|