Mathematics
Regret
100%
Online Learning
51%
Online Optimization
43%
Stochastic Optimization
30%
Convex Optimization
28%
Gradient Descent
26%
Learning
22%
Policy
21%
Stochastic Gradient
20%
Loss Function
18%
Optimization
18%
Efficient Algorithms
16%
Linear Quadratic Regulator
16%
Logistic Regression
15%
Multi-armed Bandit
14%
Open Problems
14%
Gradient
13%
Unknown
13%
Prediction
12%
Machine Learning
11%
Logarithmic
10%
Gradient Method
10%
Linear Dynamical Systems
10%
On-line Control
10%
Linear Quadratic Control
10%
Lower bound
10%
Minimax
9%
Logistics
9%
Reward
9%
Costs
9%
Convergence Rate
9%
Reinforcement Learning
8%
Mirror
8%
Optimal Algorithm
8%
Optimization Algorithm
8%
Descent
7%
Cost Function
7%
Convergence to Equilibrium
7%
Composite function
7%
Online Algorithms
7%
Trust Region
7%
Uniform Stability
7%
Adaptivity
7%
Markov Decision Process
7%
Optimal Rates
6%
Privacy
6%
Linear Control
6%
Function Approximation
6%
Learning Algorithm
6%
Rate of Convergence
6%
Engineering & Materials Science
Convex optimization
82%
Feedback
48%
Costs
20%
Learning algorithms
19%
Logistic regression
17%
Mirrors
14%
Gradient methods
13%
Linear regression
13%
Stochastic models
12%
Logistics
11%
Machine learning
10%
Markov processes
7%
Switches
7%
Cost functions
7%
Sampling
7%
Control systems
7%
Data storage equipment
7%
Identification (control systems)
6%
Support vector regression
6%
Hinges
6%
Dynamical systems
6%
Impulse response
5%
Reinforcement learning
5%
Tuning
5%
Tensors
5%
Contamination
5%
Principal component analysis
5%
Relaxation
5%
