saddle point problem
Country:
- Asia > Russia (0.28)
- Europe > Russia > Central Federal District > Moscow Oblast > Moscow (0.04)
- Asia > Middle East > Saudi Arabia (0.04)
- Asia > Middle East > Jordan (0.04)
Technology:
Private Algorithms for Stochastic Saddle Points and Variational Inequalities: Beyond Euclidean Geometry
This work was done while M. Menart was at The Ohio State University.
Country:
- North America > United States > Ohio (0.24)
- North America > Canada > Ontario > Toronto (0.14)
- South America > Chile (0.04)
- (2 more...)
Technology:
Country:
- Europe > Russia (0.14)
- Asia > Russia (0.14)
- North America > United States > Massachusetts > Middlesex County > Cambridge (0.04)
- (3 more...)
Neural Tangent Kernel: Convergence and Generalization in Neural Networks
Arthur Jacot, Franck Gabriel, Clement Hongler
This kernel is central to describe the generalization features ofANNs.
Country:
- Oceania > Australia > New South Wales > Sydney (0.04)
- North America > United States > New Jersey > Hudson County > Secaucus (0.04)
- North America > United States > Massachusetts > Middlesex County > Cambridge (0.04)
- North America > Canada (0.04)
Stochastic Primal-Dual Method for Empirical Risk Minimization with O(1) Per-Iteration Complexity
Conghui Tan, Tong Zhang, Shiqian Ma, Ji Liu
Regularized empirical risk minimization problem with linear predictor appears frequentlyinmachinelearning.
Country:
- North America > United States > Massachusetts > Suffolk County > Boston (0.04)
- North America > Canada > Quebec > Montreal (0.04)
Technology: Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning (0.32)
Country:
- Asia > Russia (0.14)
- Europe > Russia > Central Federal District > Moscow Oblast > Moscow (0.04)
- Asia > Middle East > Saudi Arabia (0.04)
Technology:
Country:
- North America > United States > Massachusetts (0.04)
- North America > Canada (0.04)
- Asia > Middle East > Jordan (0.04)
- (2 more...)
Technology:
Country:
- North America > United States > Massachusetts (0.04)
- North America > Canada (0.04)
- Asia > China > Shanghai > Shanghai (0.04)
- Asia > China > Hong Kong (0.04)
Technology:
ImprovedAlgorithmsforConvex-Concave MinimaxOptimization
This paper studies minimax optimization problemsminxmaxyf(x,y), where f(x,y) is mx-strongly convex with respect tox, my-strongly concave with respect to y and (Lx,Lxy,Ly)-smooth. Zhang et al. [42] provided the following lower bound of the gradient complexity for any first-order method: Ω q
Country:
- North America > Canada > British Columbia > Metro Vancouver Regional District > Vancouver (0.04)
- Europe > Austria > Styria > Graz (0.04)
- Asia > Middle East > Jordan (0.04)
- (2 more...)
Quasi-NewtonMethodsforSaddlePointProblems
These algorithms iterate with first-order oracle and achieve linear convergence.
Country:
- North America > United States (0.04)
- Asia > Middle East > Jordan (0.04)