Mathematics
Approximates
14%
Approximation Error
9%
Approximation Function
37%
Asymptotics
8%
Complete Matrix
11%
Computational Cost
5%
Conditionals
5%
Convergence Rate
10%
Convex Function
8%
Data Distribution
7%
Deep Learning
11%
Deep Learning Method
6%
Deep Neural Network
15%
Dimensional Data
15%
Dimensional Manifold
7%
Dynamical System
6%
Exp
6%
Factorization
10%
Function Value
29%
Gaussian Distribution
21%
Global Minimizer
10%
Global Optimum
11%
Global Solution
7%
Gradient Flow
14%
Gradient-Based Method
7%
Graphical Model
9%
Least Square
5%
Linear Convergence
6%
Linear Models
5%
Linear Predictor
9%
Linear Regression
7%
Local Minimizer
13%
Local Minimum
26%
Loss Function
12%
Low Degree
9%
M-Estimator
9%
Main Result
6%
Manifold
6%
Markov Decision Process
16%
Matrix (Mathematics)
17%
Maximum Likelihood
5%
Minimax
18%
Minimizes
10%
Model Index
11%
Model Selection
14%
Neural Net
5%
Neural Network
100%
Nonlinear
7%
Objective Function
12%
Optimal Policy
19%
Optimal Transport
9%
Optimality
36%
Polynomial
36%
Polynomial Time
22%
Probability Theory
15%
Regularity Condition
5%
Regularization
12%
Representation Learning
12%
Saddle Point
12%
Stable Manifold
6%
Stationary Point
10%
Statistics
6%
Step Size
5%
Stochastics
42%
structure learning
8%
Subgradient
7%
Subproblem
7%
Tensor
7%
Tensor Decomposition
5%
Training Data
11%
Transfer Learning
5%
Upper Bound
13%
Worst Case
5%
Computer Science
Activation Function
7%
Adversarial Machine Learning
5%
Binary Classification
6%
Conjugate Gradients
5%
Convex Function
5%
Convex Optimization
8%
Convolutional Neural Network
10%
Deep Learning
8%
Deep Learning Method
6%
Deep Neural Network
10%
Efficient Algorithm
16%
Explicit Dependence
5%
Few-Shot Learning
9%
Function Approximation
25%
Function Value
15%
Generative Adversarial Networks
9%
Global Convergence
6%
Global Optimality
9%
Gradient Descent
84%
Gradient Method
5%
High Dimensional Data
14%
Importance Sampling
9%
Kernel Method
5%
Large Language Model
14%
Layer Neural Network
23%
Learning Problem
8%
Least Squares Method
5%
Local Minimum
35%
Machine Learning
9%
Markov Decision Process
15%
multi agent
9%
Multi-Agent Reinforcement Learning
9%
Network Layer
10%
Neural Network
77%
Objective Function
7%
Optimization Algorithm
11%
Optimization Policy
8%
Optimization Problem
7%
Polynomial Time
9%
Primal-Dual
11%
Random Projection
14%
Recovery Algorithm
14%
Regularization Parameter
5%
Reinforcement Learning
43%
Representation Learning
20%
Single Index Model
7%
Stationary Point
5%
temporal difference learning
9%
Theoretical Framework
6%
Training Data
15%
Keyphrases
Black Box
9%
Complexity Bounds
6%
Dual Random Projection
9%
Function Approximation
5%
Global Optimum
9%
Gradient Descent
38%
Gradient Method
8%
Hessian Sketch
9%
Implicit Bias
11%
Importance Sampling
9%
Landscape Design
9%
Lazy Training
5%
Local Minimizer
7%
Markov Decision Process
7%
Max-margin
7%
Mixed Graphical Model
9%
Neural Network
20%
Neural Tangent Kernel
16%
Nonconvex Optimization
5%
Optimal Sample Complexity
11%
Overparametrized Neural Network
7%
Population Loss
5%
Q-learning
9%
Rectified Linear Unit (ReLU)
7%
Reinforcement Learning
5%
Sample Complexity
25%
Search Algorithm
5%
Shallow Neural Network
5%
Single-index Model
9%
Spurious Local Minima
9%
Stochastic Gradient Descent
15%
Temporal Difference Learning
9%
Training Data
7%
