On Nonconvex Optimization for Machine Learning: Gradients, Stochasticity, and Saddle Points.
Chi JinPraneeth NetrapalliRong GeSham M. KakadeMichael I. JordanPublished in: J. ACM (2021)
Keyphrases
- machine learning
- saddle points
- saddle point
- optimization problems
- decision trees
- feature selection
- objective function
- information extraction
- convex optimization
- machine learning algorithms
- penalty function
- kernel methods
- evolutionary algorithm
- computer vision
- learning algorithm
- learning tasks
- inductive logic programming
- numerical methods
- primal dual