What is he best known for?
The fields of study he is best known for:
- Mathematical optimization
- Statistics
- Algorithm
Yinyu Ye mainly investigates Mathematical optimization, Algorithm, Interior point method, Linear programming and Semidefinite programming.
His Mathematical optimization research is multidisciplinary, incorporating perspectives in Wireless sensor network and Second-order cone programming, Convex optimization.
He mostly deals with Optimization problem in his studies of Algorithm.
His studies in Linear programming integrate themes in fields like Function and Generalization.
He has researched Semidefinite programming in several fields, including Semidefinite embedding, Gradient descent, Graph theory, Relaxation and Euclidean distance.
His work deals with themes such as Statistics, Method of steepest descent, Conic section and Calculus, which intersect with Nonlinear programming.
His most cited work include:
- Linear and nonlinear programming (5174 citations)
- Semidefinite Relaxation of Quadratic Optimization Problems (1824 citations)
- Distributionally Robust Optimization Under Moment Uncertainty with Application to Data-Driven Problems (857 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of investigation include Mathematical optimization, Algorithm, Linear programming, Interior point method and Combinatorics.
His Mathematical optimization study often links to related topics such as Convex optimization.
Much of his study explores Linear programming relationship to Function.
His Interior point method study integrates concerns from other disciplines, such as Point, Numerical analysis and Applied mathematics.
His research in Combinatorics focuses on subjects like Discrete mathematics, which are connected to Polynomial.
His Semidefinite programming research includes themes of Wireless sensor network, Graph, Semidefinite embedding and Relaxation.
He most often published in these fields:
- Mathematical optimization (49.21%)
- Algorithm (21.47%)
- Linear programming (20.16%)
What were the highlights of his more recent work (between 2017-2021)?
- Mathematical optimization (49.21%)
- Interior point method (20.16%)
- Linear programming (20.16%)
In recent papers he was focusing on the following fields of study:
His primary areas of study are Mathematical optimization, Interior point method, Linear programming, Discrete mathematics and Markov decision process.
As part of his studies on Mathematical optimization, Yinyu Ye often connects relevant subjects like Estimator.
His Interior point method study incorporates themes from Point and Feasible region.
Yinyu Ye combines subjects such as Penalty method, Nonlinear programming, Binary logarithm, Distribution and Online algorithm with his study of Linear programming.
His work carried out in the field of Markov decision process brings together such families of science as Range, Sample and Reinforcement learning.
The various areas that Yinyu Ye examines in his Optimization problem study include Computational complexity theory, Feature selection and Rendering.
Between 2017 and 2021, his most popular works were:
- Variance reduced value iteration and faster algorithms for solving markov decision processes (63 citations)
- Near-Optimal Time and Sample Complexities for Solving Markov Decision Processes with a Generative Model (58 citations)
- Near-Optimal Time and Sample Complexities for Solving Discounted Markov Decision Process with a Generative Model (23 citations)
In his most recent research, the most cited papers focused on:
- Statistics
- Algorithm
- Mathematical optimization
His scientific interests lie mostly in Mathematical optimization, Convergence, Coordinate descent, Upper and lower bounds and Markov decision process.
His Mathematical optimization study frequently links to other fields, such as Nonlinear programming.
His Convergence research focuses on subjects like Random permutation, which are linked to Rate of convergence, Convex optimization, Quadratic programming and Iterated function.
His biological study spans a wide range of topics, including Crowdsourcing, Logarithm, Regret and Combinatorics.
His study focuses on the intersection of Feasible region and fields such as Penalty method with connections in the field of Linear programming.
His work is dedicated to discovering how Interior point method, Matrix are connected with Algorithm and other disciplines.
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
