Skip to main navigation
Skip to search
Skip to main content
Princeton University Home
Help & FAQ
Link opens in a new tab
Search content at Princeton University
Home
Profiles
Research units
Facilities
Projects
Research output
Press/Media
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
5311
Citations
33
h-index
Calculated based on number of publications stored in Pure and citations from Scopus
2012
2025
Research activity per year
Overview
Fingerprint
Network
Projects
(3)
Research output
(81)
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
Keyphrases
Sample Complexity
36%
Non-convexity
35%
Reinforcement Learning
33%
Gradient Descent
27%
Regret
23%
Near-optimal
22%
Minimax Optimization
20%
Minimax
15%
Markov Game
14%
Bandit Feedback
14%
Low-rank
13%
Machine Learning
13%
Sample Efficiency
12%
Partially Observable Markov Decision Process
12%
Gradient Ascent
11%
Markov Decision Process
10%
Self-play Algorithm
10%
General-sum Games
10%
Optimization Algorithm
9%
Linear Function Approximation
8%
Class Function
8%
Optimal Policy
8%
Generative Adversarial Networks
8%
Policy Optimization
8%
Representation Learning
8%
Partially Observable
8%
Global Convergence
8%
Local Optimality
8%
Convex-concave Minimax Problem
8%
Nonconvex Optimization
7%
Coarse Correlated Equilibrium
7%
Function Approximation
7%
Multiplayer Games
7%
Convergence Rate
7%
Latent State
7%
Hardness Results
7%
Reinforcement Learning Algorithm
6%
Efficient Policy
6%
Multi-agent Reinforcement Learning
6%
Number of States
6%
High Probability
6%
Stochastic Gradient Descent
6%
Two-player
6%
Convex-concave
6%
Adversarial Training
6%
Regret Bounds
6%
Gradient Method
6%
V-learning
6%
Near-optimal Algorithm
6%
Approximate Nash Equilibrium
6%
Local Convergence
6%
Self-play
5%
Eigenvector
5%
Two-time Scale
5%
Transition Function
5%
Bandits
5%
Nash Equilibrium
5%
Online Environment
5%
Number of Steps
5%
Q-learning
5%
Shared Representations
5%
Correlated Equilibrium
5%
Eigenvector Computation
5%
Value Function
5%
Reward Function
5%
Two-player Zero-sum Game
5%
Two-layer Neural Network
5%
Mathematics
Stochastics
36%
Convex
35%
Minimax
32%
Polynomial
31%
Approximates
31%
Matrix (Mathematics)
26%
Saddle Point
24%
Nash Equilibrium
23%
Approximation Function
19%
Optimal Policy
17%
Partially Observable Markov Decision Process
16%
Stationary Point
14%
Local Minimum
13%
Probability
13%
Linear Function
13%
Optimality
12%
Action Space
12%
Convex Function
11%
Multi-Agent Reinforcement Learning
11%
Total Number
10%
Maximum Likelihood
10%
Convergence Rate
10%
Worst Case
9%
Markov Decision Process
8%
Feature Space
8%
Neural Network
8%
Complete Matrix
8%
Initial Step
8%
Transition Function
8%
Open Question
7%
Asymmetric
6%
Principal Component Analysis
6%
Local Convergence
6%
Objective Function
6%
Excess Risk
6%
Joint Action
6%
Covariate
6%
Eigenvector
5%
Positive Definite Matrix
5%
Numerical Linear Algebra
5%
Concave Function
5%
Polynomial Time
5%
Intrinsic Property
5%
Observation Space
5%
Starting Point
5%
Computer Science
Reinforcement Learning
100%
Function Approximation
30%
Markov Decision Process
26%
Nash Equilibrium
24%
Efficient Algorithm
24%
multi agent
18%
Machine Learning
16%
Learning Algorithm
15%
Multi-Agent Reinforcement Learning
14%
Stochastic Gradient Descent
13%
Representation Learning
13%
Learning System
13%
Optimization Algorithm
12%
Partial Observability
11%
Optimal Algorithm
10%
Likelihood Estimation
9%
maximum-likelihood
9%
Theoretical Framework
9%
Risk Minimization
9%
Linear Representation
8%
Linear Function
8%
Gradient Descent
8%
Transition Function
8%
Large State Space
8%
Simple Algorithm
7%
Subclasses
6%
Sequential Decision Making
6%
Condition Number
6%
Measure of Complexity
6%
Contrastive Learning
6%
Model-Based Reinforcement Learning
5%
Probability
5%
Experimental Result
5%
Information Set
5%
Stationary Point
5%
Large Language Model
5%
Polynomial Time
5%
Learning Problem
5%
