Mathematics
Neural Network
100%
Stochastics
42%
Approximation Function
38%
Optimality
37%
Function Value
25%
Polynomial
24%
Local Minimum
23%
Polynomial Time
23%
Minimax
19%
Optimal Policy
19%
Matrix (Mathematics)
17%
Dimensional Data
16%
Gaussian Distribution
16%
Deep Neural Network
16%
Probability Theory
15%
Approximates
15%
Model Selection
14%
Gradient Flow
14%
Local Minimizer
14%
Objective Function
13%
Saddle Point
13%
Loss Function
12%
Regularization
12%
Global Optimum
12%
Deep Learning
12%
Upper Bound
11%
Minimizes
11%
Representation Learning
11%
Stationary Point
10%
Global Minimizer
10%
Convergence Rate
10%
Factorization
10%
Linear Predictor
9%
M-Estimator
9%
Complete Matrix
9%
Optimal Transport
9%
Graphical Model
9%
Approximation Error
9%
Markov Decision Process
9%
Convex Function
8%
Asymptotics
8%
structure learning
8%
Dimensional Manifold
8%
Data Distribution
8%
Linear Regression
8%
Training Data
7%
Subproblem
7%
Gradient-Based Method
7%
Principal Component Analysis
7%
Subgradient
7%
Tensor
7%
Global Solution
7%
Exp
6%
Stable Manifold
6%
Manifold
6%
Statistics
6%
Dynamical System
6%
Tensor Decomposition
6%
Regularity Condition
6%
Main Result
6%
Step Size
5%
Computational Cost
5%
Conditionals
5%
Neural Net
5%
Transfer Learning
5%
Model Index
5%
Computer Science
Gradient Descent
76%
Neural Network
75%
Local Minimum
31%
Reinforcement Learning
29%
Function Approximation
21%
Representation Learning
21%
Layer Neural Network
19%
Efficient Algorithm
14%
Recovery Algorithm
14%
High Dimensional Data
14%
Random Projection
14%
Primal-Dual
12%
Convolutional Neural Network
11%
Markov Decision Process
11%
Function Value
10%
Training Data
10%
Deep Neural Network
10%
Optimization Algorithm
10%
Multi-Agent Reinforcement Learning
9%
Generative Adversarial Networks
9%
Few-Shot Learning
9%
temporal difference learning
9%
Importance Sampling
9%
multi agent
9%
Network Layer
9%
Machine Learning
9%
Global Optimality
9%
Polynomial Time
9%
Learning Problem
9%
Convex Optimization
8%
Optimization Policy
8%
Deep Learning
8%
Optimization Problem
8%
Objective Function
7%
Activation Function
7%
Global Convergence
6%
Theoretical Framework
6%
Binary Classification
6%
Explicit Dependence
6%
Regularization Parameter
5%
Adversarial Machine Learning
5%
Stationary Point
5%
Conjugate Gradients
5%
Convex Function
5%
Keyphrases
Gradient Descent
30%
Neural Network
21%
Sample Complexity
21%
Stochastic Gradient Descent
15%
Neural Tangent Kernel
11%
Optimal Sample Complexity
11%
Global Optimum
9%
Temporal Difference Learning
9%
Q-learning
9%
Dual Random Projection
9%
Hessian Sketch
9%
Importance Sampling
9%
Landscape Design
9%
Mixed Graphical Model
9%
Black Box
9%
Gradient Method
9%
Local Minimizer
8%
Overparametrized Neural Network
7%
Training Data
7%
Rectified Linear Unit (ReLU)
7%
Complexity Bounds
7%
Population Loss
6%
Shallow Neural Network
6%
Search Algorithm
5%
Nonconvex Optimization
5%
Lazy Training
5%
