Keyphrases
Bandit Learning
28%
Continuous Action
28%
Contextual Bandits
28%
Tsybakov Noise
28%
Learning Halfspaces
28%
Active Learning
28%
Label Complexity
27%
Half-space
23%
Regret Bounds
20%
Adaptivity
17%
Continuous Action Space
14%
Abstract Policies
14%
Point Labels
14%
Version Space
14%
Example-based Explanations
14%
Safe Model
14%
Technical Study
14%
Attribute-efficient Learning
14%
Mistake Bound
14%
Linear Separability
14%
Adaptive Algorithm
14%
Massart Noise
14%
Batch Mode Active Learning
14%
Smoothness Parameter
14%
Warm-starting
14%
Data Dependency
14%
Bandit Feedback
14%
Swin Transformer
14%
Annoying Noise
14%
Littlestone Dimension
14%
Class Action
14%
Fairness Auditing
14%
Lipschitz
14%
Comparative Epigenomics
14%
Agnostic Active Learning
14%
Multi-objective Reinforcement Learning
14%
Explore-then-Commit
14%
Feedback Aggregation
14%
Heterogeneous Feedback
14%
Mechanism Knowledge
14%
Bounded Noise
14%
Unimodal Bandits
14%
Upper Confidence Bound Algorithm
14%
Structured Bandits
14%
Robust Transfer
14%
Nonconvex Optimization
14%
Low-rank Matrix Approximation
14%
Human-AI
14%
Kullback-Leibler
14%
Bounded Rewards
14%
Computer Science
Active Learning
100%
Learning Algorithm
72%
Confidence Bound
42%
Efficient Algorithm
40%
Continuity Assumption
28%
Reinforcement Learning
21%
Sampling Algorithm
21%
Unlabeled Example
17%
Unlabeled Data
17%
Data Distribution
17%
Optimistic Algorithm
14%
Tractable Algorithm
14%
Boundary Point
14%
Multiple Agents
14%
World Application
14%
Swin Transformer
14%
Online Learning
14%
And-States
14%
Spectrum Efficiency
14%
Adaptive Algorithm
14%
Multiclass Problem
14%
Nonlinear Regression
14%
Multitask Learning
14%
Data Source
14%
Supervised Learning
14%
Bound Algorithm
14%
Heterogeneous Network
14%
Convex Optimization
14%
Electronic Learning
14%
Annotation
14%
Markov Decision Process
9%
Cellular Network
7%
Knowledge Transfer
7%
Sequential Decision Making
7%
Optimal Performance
7%
Sparsity
7%
Wireless Technologies
7%
Action-Set
7%
Outlier Removal
7%
Data Aggregation
7%
Linear Optimization
7%
Synthetic Data
7%
Performance Guarantee
7%
Uniform Distribution
7%
Individual Task
7%
Risk Minimization
7%
Unimodal Function
7%
Clustering Structure
7%
Stationary Point
7%
Problem Selection
7%
Mathematics
Optimality
42%
Dependent Data
28%
Lower and upper bounds
28%
Action Space
28%
Upper Confidence Bound
28%
Asymptotics
28%
Loss Function
28%
Data Distribution
28%
Estimation Method
14%
Upper Bound
14%
Linear Separability
14%
Covariate
14%
Hidden State
14%
Hidden Markov Model
14%
Learning Task
14%
Millimeter Wave Communication
14%
Wide Range
14%
Stationary Point
14%
Approximates
14%
Design Experiment
14%
Prior State
14%
Finite Time
10%
Worst Case
10%
Synthetic Data
7%
Tree Structure
7%
Frequentist
7%
Graphical Model
7%
Spectral Method
7%
Open Problem
7%
stopping time τ
7%
Latent Variable Model
7%
Iterative Method
7%
Complexity Space
7%
Gaussian Distribution
7%
Closed Form
7%
Probability Theory
7%