Keyphrases
Regret
100%
Regret Minimization
62%
Markov Decision Process
56%
Online Algorithms
56%
Regret Bounds
55%
Bandits
51%
Learning Algorithm
43%
Reinforcement Learning
42%
Sample Complexity
40%
Online Learning
38%
Nash Equilibrium
35%
Competitive Ratio
32%
Multi-arm Bandit
32%
Tight
28%
Near-optimal
28%
Decision Tree
27%
Quality of Service
26%
Non-stochastic
26%
Buyers
25%
Adversary
24%
Loss Function
22%
Learnability
22%
Bandit Feedback
22%
Greedy Algorithm
20%
Differential Privacy
19%
Competitive Analysis
19%
Differentiated Services
19%
Agnostic
19%
Machine Learning
19%
Optimal Policy
19%
Oracle
19%
Seller
19%
Payoff
19%
Polynomial Time
18%
Domain Adaptation
18%
Differentially Private
18%
Optimal Regret
17%
Generalization Bounds
17%
Minimization Algorithm
17%
Incentive Mechanism
16%
Greedy
15%
Packet Scheduling
15%
Radio Networks
15%
Social Welfare
15%
Log-log
15%
Competitive Algorithm
15%
Tight Bounds
15%
Full Information
15%
Number of Packets
15%
High Probability
14%
Computer Science
Learning Algorithm
70%
on-line algorithm
65%
Markov Decision Process
52%
Nash Equilibrium
49%
Reinforcement Learning
49%
Competitive Ratio
38%
Approximation (Algorithm)
35%
Electronic Learning
33%
Efficient Algorithm
31%
Quality of Service
30%
Differential Privacy
28%
Decision Tree
27%
Communication Network
26%
Machine Learning
25%
Greedy Algorithm
25%
Polynomial Time
24%
Learning System
23%
Domain Adaptation
22%
Sampling Algorithm
22%
Differentiated Service
20%
Competitive Analysis
19%
Time Complexity
19%
Learning Problem
19%
Multiclass Classification
17%
Uniform Distribution
17%
Mechanism Design
16%
Packet Scheduling
15%
Control Algorithm
15%
Function Approximation
14%
Binary Classification
13%
Shared Memory Switch
12%
Max-Min Fairness
12%
Information Unit
12%
Computational Complexity
12%
Buffer Management
12%
Computation Tree
12%
Proof Technique
12%
Flow Control
12%
Resource Allocation
12%
Load Balancing
12%
Target Function
12%
Convex Optimization
11%
Universal Hashing
11%
Shared Memory
11%
Optimal Algorithm
11%
Weighted Average
11%
Job Scheduling
11%
Bandwidth Allocation
11%
State Space
10%
Transition Function
10%
Mathematics
Stochastics
69%
Markov Decision Process
52%
Probability Theory
43%
Upper Bound
41%
Main Result
38%
Minimizes
37%
Time Step
34%
Polynomial Time
32%
Approximates
32%
Loss Function
25%
Nash Equilibrium
24%
Polynomial
24%
Lower and upper bounds
24%
Worst Case
23%
Optimal Policy
22%
Uniform Distribution
20%
Min-Max
19%
Binary Classification
19%
Integer
17%
Minimax
17%
False Negative
15%
Decision Tree
15%
Edge
15%
Function Value
15%
Arbitrary Distribution
14%
Running Time
13%
Partially Observable Markov Decision Process
12%
Probability Distribution
12%
Convergence Rate
12%
Random Variable
11%
Approximation Function
11%
Action Space
10%
Black Box
10%
Decision Maker
10%
Underlying Distribution
9%
Wide Class
9%
Competitive Ratio
9%
Bicriteria
9%
Weighted Average
9%
Error Rate
9%
Multiplicative
9%
Open Question
9%
Permutation
9%
Cost Function
9%
VC Dimension
9%
Training Data
8%
Fixed Price
8%
Square Root
8%
Optimality
8%
Uniform Convergence
8%
