Keyphrases
Regret
69%
Stochastic Gradient Descent
33%
Bandits
32%
Online Learning
32%
Regret Bounds
27%
Loss Function
24%
Stochastic Convex Optimization
23%
Stochastic Optimization
21%
Gradient Descent
20%
Online Convex Optimization
18%
Multi-arm Bandit
17%
Strongly Convex
16%
Switching Costs
16%
Tight
15%
Minimax Regret
15%
Bandit Feedback
15%
Optimal Rate
15%
Optimal Regret
14%
Online Optimization
14%
Convergence Rate
14%
Learning Problems
14%
Computationally Efficient Algorithms
12%
Gradient Method
12%
Multi-armed Bandit Problem
12%
Optimization Algorithm
11%
Accelerated Gradient Method
10%
Adversarial Corruptions
10%
Feedback Graph
10%
Linear Quadratic Regulator
10%
Linear Control
10%
Nonconvex
10%
Stochastic multi-armed Bandits
10%
Linear Regression
10%
Empirical Risk Minimization
9%
Bandit Convex Optimization
9%
Fast Rates
9%
Cost Function
9%
Unknown Dynamics
9%
Adagrad
9%
Implicit Bias
9%
Generalization Performance
9%
Convex Optimization
8%
Linear Dynamical Systems
8%
Adaptive Adversary
8%
Smooth Optimization
8%
Differentially Private
8%
Markov Decision Process
8%
Non-convex Cost Function
8%
Gradient Step
8%
Near-optimal
7%
Mathematics
Stochastics
100%
Loss Function
40%
Upper Bound
25%
Minimax
23%
Open Problem
21%
Convergence Rate
14%
Regularization
14%
Approximates
11%
Linear Controller
10%
Linear Time
10%
Linear Dynamical Systems
10%
Multiplicative
10%
Variance
9%
Linear Quadratic Control
9%
Linear Regression Analysis
9%
Markov Decision Process
8%
Probability Theory
8%
Matrix (Mathematics)
7%
Empirical Risk Minimization
7%
Cost Function
7%
Square Root
7%
Fixed Price
7%
Support Vector Machine
7%
Exp
7%
Free Parameter
7%
Main Result
5%
Control System
5%
Logistic Regression
5%
Optimal Policy
5%
Open Question
5%
Lower and upper bounds
5%
Computer Science
Electronic Learning
33%
Convex Optimization
28%
Efficient Algorithm
23%
Stochastic Optimization
17%
Learning Problem
13%
Convergence Rate
12%
Gradient Descent
11%
Linear Controller
10%
Fundamental Problem
10%
Markov Decision Process
9%
Optimization Algorithm
7%
Sequential Decision Making
7%
Internal State
7%
Decision Maker
7%
Adaptive Algorithm
7%
Fast Convergence
7%
Optimization Policy
7%
Dynamical System
7%
Free Parameter
7%
Delay Distribution
5%
Learning System
5%
Machine Learning
5%
Optimization Problem
5%
