Keyphrases
Regret
69%
Stochastic Gradient Descent
34%
Bandits
30%
Online Learning
30%
Regret Bounds
24%
Stochastic Convex Optimization
22%
Stochastic Optimization
22%
Loss Function
21%
Online Convex Optimization
18%
Gradient Descent
17%
Bandit Feedback
15%
Linear Quadratic Regulator
15%
Optimal Rate
15%
Multi-arm Bandit
14%
Strongly Convex
14%
Gradient Method
13%
Computationally Efficient Algorithms
13%
Switching Costs
13%
Tight
13%
Convergence Rate
12%
Minimax Regret
12%
Optimal Regret
12%
Online Optimization
12%
Fast Rates
12%
Learning Problems
11%
Adagrad
10%
Multi-armed Bandit Problem
10%
Convex Optimization
10%
Linear Regression
10%
Optimization Algorithm
9%
Unknown Dynamics
9%
Accelerated Gradient Method
9%
Adversarial Corruptions
9%
Feedback Graph
9%
Linear Control
9%
Nonconvex
8%
Stochastic multi-armed Bandits
8%
Online Learning Algorithm
8%
Empirical Risk Minimization
8%
Bandit Convex Optimization
8%
Convergence Guarantee
7%
Online Prediction
7%
Cost Function
7%
Differentially Private
7%
Implicit Bias
7%
Generalization Performance
7%
Computationally Efficient
7%
Square Root
7%
Oracle
7%
Linear Dynamical Systems
7%
Mathematics
Stochastics
100%
Loss Function
34%
Upper Bound
24%
Open Problem
21%
Minimax
20%
Linear Quadratic Control
15%
Multiplicative
12%
Linear Time
12%
Regularization
11%
Variance
11%
Convergence Rate
11%
Open Question
10%
Approximates
10%
Matrix (Mathematics)
9%
Control System
9%
Linear Controller
9%
Linear Dynamical Systems
9%
Square Root
9%
Empirical Risk Minimization
9%
Exp
9%
Linear Regression Analysis
8%
Main Result
8%
Markov Decision Process
6%
Probability Theory
6%
Tensor
6%
Cost Function
6%
Fixed Price
6%
Support Vector Machine
6%
Free Parameter
6%
State Distribution
6%
Invariant System
6%
Feasible Solution
6%
Optimal Policy
6%
Transition Matrix
6%
Rate of Convergence
5%
Logistic Regression
5%
Convex Function
5%
Computer Science
Electronic Learning
31%
Convex Optimization
29%
Stochastic Optimization
27%
Efficient Algorithm
24%
Convergence Rate
17%
Gradient Descent
12%
Learning Problem
11%
Fundamental Problem
11%
Optimization Algorithm
10%
Linear Controller
9%
Fast Convergence
9%
Learning Algorithm
9%
Markov Decision Process
7%
Learning System
7%
Machine Learning
7%
Logistic Regression
6%
Gradient Method
6%
Sequential Decision Making
6%
Internal State
6%
Decision Maker
6%
Adaptive Algorithm
6%
Optimization Policy
6%
Dynamical System
6%
Free Parameter
6%
Multiclass Classification
6%
Regularization
6%
Neural Network
6%
Transition Matrix
6%
Risk Minimization
6%
Concave Function
6%
