Statements (70)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:Artificial_Intelligence
|
| gptkbp:adapted_into |
stochastic optimization
|
| gptkbp:applies_to |
gptkb:robot
real-time systems logistic regression time series forecasting smooth functions non-smooth optimization problems |
| gptkbp:based_on |
momentum concept
|
| gptkbp:can_be_used_with |
other optimization techniques
|
| gptkbp:developed_by |
gptkb:Yurii_Nesterov
|
| gptkbp:difficulty |
O(n) per iteration
|
| gptkbp:has_achievements |
optimal convergence rate
|
| gptkbp:has_programs |
image processing
|
| https://www.w3.org/2000/01/rdf-schema#label |
Nesterov's method
|
| gptkbp:improves |
gradient descent
|
| gptkbp:is_a |
iterative method
|
| gptkbp:is_analyzed_in |
numerical experiments
|
| gptkbp:is_cited_in |
scholarly articles
theses and dissertations |
| gptkbp:is_compared_to |
gptkb:Adam_optimizer
traditional gradient descent RM Sprop |
| gptkbp:is_considered |
performance analysis
hyperparameter tuning model training |
| gptkbp:is_considered_as |
a state-of-the-art method
|
| gptkbp:is_discussed_in |
gptkb:academic_conferences
optimization seminars |
| gptkbp:is_effective_against |
large-scale problems
minimizing convex functions |
| gptkbp:is_evaluated_by |
theoretical analysis
benchmark tests SGD with momentum |
| gptkbp:is_explored_in |
research papers
graduate studies optimization workshops optimization courses |
| gptkbp:is_implemented_in |
gptkb:Graphics_Processing_Unit
gptkb:scikit-learn gptkb:Py_Torch various programming languages |
| gptkbp:is_influential_in |
theoretical computer science
|
| gptkbp:is_part_of |
machine learning frameworks
gradient-based optimization methods algorithmic strategies advanced optimization techniques numerical optimization techniques |
| gptkbp:is_popular_in |
data science
|
| gptkbp:is_recognized_for |
its efficiency
its theoretical foundation its robustness |
| gptkbp:is_related_to |
Lipschitz continuity
first-order methods |
| gptkbp:is_studied_in |
convergence properties
optimization literature |
| gptkbp:is_used_for |
feature selection
training neural networks |
| gptkbp:is_used_in |
gptkb:software_framework
financial modeling reinforcement learning support vector machines big data analysis |
| gptkbp:is_utilized_in |
computer vision
deep learning natural language processing |
| gptkbp:provides |
accelerated convergence
|
| gptkbp:used_in |
convex optimization
|
| gptkbp:bfsParent |
gptkb:Nesterov_Accelerated_Gradient
|
| gptkbp:bfsLayer |
5
|