Skip to main navigation
Skip to search
Skip to main content
Princeton University Home
Help & FAQ
Home
Profiles
Research units
Facilities
Projects
Research output
Press/Media
Search by expertise, name or affiliation
Contact Expert
View Scopus Profile
Chi Jin
Electrical and Computer Engineering
Princeton Language and Intelligence (PLI)
Former affiliation
Center for Statistics & Machine Learning
h-index
3655
Citations
28
h-index
Calculated based on number of publications stored in Pure and citations from Scopus
2012
2024
Research activity per year
Overview
Fingerprint
Network
Projects
(4)
Research output
(65)
Similar Profiles
(6)
Fingerprint
Dive into the research topics where Chi Jin is active. These topic labels come from the works of this person. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Mathematics
Polynomial
48%
Approximates
44%
Approximation Function
43%
Stochastics
36%
Matrix (Mathematics)
32%
Optimal Policy
29%
Function Value
28%
Minimax
26%
Total Number
23%
Partially Observable Markov Decision Process
23%
Saddle Point
23%
Local Minimum
19%
Linear Function
19%
Nash Equilibrium
18%
Optimality
16%
Convex Function
16%
Convergence Rate
14%
Stationary Point
12%
Feature Space
11%
Positive Definite Matrix
11%
Local Convergence
11%
Neural Network
11%
Numerical Linear Algebra
11%
Principal Component Analysis
9%
Starting Point
9%
Least Square
8%
Approximation of Function
8%
Black Box
8%
Probability Theory
8%
Maximum Likelihood Estimation
8%
Eigenvector
8%
Concave Function
7%
Objective Function
7%
Open Question
7%
Wide Range
6%
Action Space
5%
Running Time
5%
Markov Decision Process
5%
Regularization
5%
Exponential Time
5%
Complete Matrix
5%
Monte Carlo
5%
Probability Proportional
5%
Rapid Growth
5%
Optimization Property
5%
Exploratory
5%
Independency
5%
Excess Risk
5%
Statistics
5%
Free Parameter
5%
Generalized Eigenvector
5%
Lower Confidence Bound
5%
Sample Efficiency
5%
Tensor Decomposition
5%
Arbitrary Number
5%
Canonical Correlation Analysis
5%
Fundamental Set
5%
Positive Definite
5%
K-Group
5%
Probability Measure
5%
Representation Learning
5%
Continuous Domain
5%
Computer Science
Reinforcement Learning
100%
Gradient Descent
31%
Markov Decision Process
28%
Efficient Algorithm
26%
Nash Equilibrium
21%
Machine Learning
19%
Function Approximation
17%
Partial Observability
15%
Learning Algorithm
14%
Simple Algorithm
14%
Theoretical Framework
13%
Local Minimum
11%
Multi-Agent Reinforcement Learning
11%
And-States
11%
Learning Problem
10%
Subclasses
10%
Linear Representation
9%
Representation Learning
8%
Extensive Form Game
8%
Mild Condition
8%
Sequential Decision Making
8%
Stationary Point
8%
Model-Based Reinforcement Learning
8%
Likelihood Estimation
8%
maximum-likelihood
8%
Experimental Result
7%
multi agent
7%
Risk Minimization
7%
Optimization Problem
6%
Convergence Rate
6%
Optimal Algorithm
5%
Physical Parameter
5%
Large State Space
5%
Layer Neural Network
5%
Neural Network
5%
Optimization Framework
5%
Concave Function
5%
Optimal Representation
5%
Generative Adversarial Networks
5%
Free Parameter
5%
Autonomous Driving
5%
Gradient Descent Method
5%
Transfer Learning
5%
Condition Number
5%
Support Vector Machine
5%
Minimax Problem
5%
Past Experience
5%
Continuous Data
5%
Starting Point
5%
State Space
5%
Principal Components
5%
Component Analysis
5%
Feature Space
5%
Transition Function
5%
Fundamental Limit
5%
Linear Classifier
5%
Training Sample
5%
Simulated Environment
5%
Continuous Domain
5%
Rationalizable Strategy
5%
Machine Learning
5%
Learning System
5%
Similarity Function
5%
Federated Learning
5%
Multiple Client
5%
Latent Variable Model
5%
Superior Performance
5%
Communication Complexity
5%
Variance Reduction
5%
Order Function
5%
Smoothness Assumption
5%
Polynomial Time
5%
Optimization Algorithm
5%
Keyphrases
Reinforcement Learning
33%
Gradient Descent
31%
Function Approximation
21%
Regret
21%
Nonconvex
20%
Linear Function Approximation
16%
Sample Complexity
15%
Markov Games
14%
Sample-Efficient Reinforcement Learning
11%
Reinforcement Learning Problems
11%
Bellman
10%
Number of States
9%
Nonconvex Optimization
9%
Stochastic Gradient Descent
9%
Gradient Method
8%
Sample-efficient Learning
8%
Sampling Efficiency
8%
Reinforcement Learning Algorithm
7%
Partially Observable Markov Decision Process
7%
Machine Learning
7%
Spurious Local Minima
7%
Natural Policy Gradient
7%
Convex Optimization
7%
Multi-agent Reinforcement Learning
6%
Stationary Point
6%
Gradient Ascent
5%
Latent State
5%
Near-optimal Policy
5%
Markov Decision Process
5%
Task Diversity
5%
Matching Matrix
5%
Bandit Feedback
5%
Cubic Regularization
5%
Fundamental Limits
5%
Local Minima
5%
Generic Model
5%
Optimization for Machine Learning
5%
Tag Matrix Completion
5%
Efficient Policy
5%
Large State Space
5%
Exploiter
5%
Representation Learning
5%
Optimal Representation
5%
Accelerated Gradient Method
5%
Minimax Optimization
5%
Hardness Results
5%
Partially Observable Markov Games
5%
Optimization Framework
5%
Reinforcement Learning from Human Feedback
5%
General-sum Games
5%
Multi-task
5%
Data Releasing
5%
Proximal Policy Optimization Algorithm
5%
Near-optimal
5%
Competitive Reinforcement
5%
Empirical Risk
5%
Policy Optimization
5%
Modeling Algorithm
5%
Reward-free Exploration
5%
Weighted Gradient
5%
Learning Sample
5%
Sequential Decision Making
5%
Parameter-free
5%
Adversary
5%
Nonconcave
5%
Partially Observable
5%
Interactive Reinforcement Learning
5%
Minimax Problem
5%
Fast Eigenvector Computation
5%
Margin Bound
5%
Shift-and-invert Preconditioning
5%
Sampling numbers
5%
Linear Bandits
5%
Exponential Time
5%
K-group
5%
Random Context
5%
Global Convergence
5%
Constrained Reinforcement Learning
5%
Stochastic Proximal Point
5%
Second-order Similarity
5%
Unsupervised Pre-training
5%
Swap Regret
5%
Equilibrium Finding
5%
Sim-to-real Transfer
5%
Continuous Domain
5%
Partial Observation
5%
Value Function
5%
Least Square Value
5%
