What is he best known for?
The fields of study he is best known for:
- Statistics
- Computer network
- Mathematical analysis
Communication channel, Channel capacity, Computer network, Secrecy and Topology are his primary areas of study.
The Communication channel study combines topics in areas such as Transmitter, Relay, Information-theoretic security and Computer security.
He works mostly in the field of Transmitter, limiting it down to concerns involving Channel state information and, occasionally, Fading and Gaussian noise.
His Channel capacity research is multidisciplinary, relying on both Signal-to-noise ratio, Mathematical optimization, Decoding methods and Additive white Gaussian noise.
His work in Secrecy covers topics such as Entropy which are related to areas like Message authentication code, Decodes and Covariance matrix.
Yingbin Liang has included themes like Wiretap channels and MIMO in his Topology study.
His most cited work include:
- Secure Communication Over Fading Channels (899 citations)
- Information Theoretic Security (760 citations)
- Multiple-Access Channels With Confidential Messages (277 citations)
What are the main themes of his work throughout his whole career to date?
Yingbin Liang mainly investigates Communication channel, Computer network, Algorithm, Topology and Transmitter.
His study in Communication channel is interdisciplinary in nature, drawing from both Decoding methods and Secrecy.
He has researched Computer network in several fields, including Relay channel, Relay, Broadcast channels and Computer security.
His work carried out in the field of Algorithm brings together such families of science as Gradient descent, Rate of convergence, Convergence and Logarithm.
His Topology research includes elements of Dirty paper coding, Precoding, Gaussian noise and Spatial correlation.
Within one scientific family, Yingbin Liang focuses on topics pertaining to Channel state information under Fading, and may sometimes address concerns connected to Additive white Gaussian noise.
He most often published in these fields:
- Communication channel (35.11%)
- Computer network (20.92%)
- Algorithm (20.57%)
What were the highlights of his more recent work (between 2019-2021)?
- Algorithm (20.57%)
- Rate of convergence (13.48%)
- Convergence (12.06%)
In recent papers he was focusing on the following fields of study:
His scientific interests lie mostly in Algorithm, Rate of convergence, Convergence, Reinforcement learning and Gradient descent.
His work on Bilevel optimization as part of general Algorithm study is frequently connected to Initialization, therefore bridging the gap between diverse disciplines of science and establishing a new relationship between them.
The concepts of his Rate of convergence study are interwoven with issues in Computational complexity theory, Q-learning and Mathematical optimization.
His work deals with themes such as Path and Backtracking, which intersect with Convergence.
His studies in Gradient descent integrate themes in fields like Function, Optimization problem, Sublinear function and Minimax.
His Channel capacity study deals with the bigger picture of Communication channel.
Between 2019 and 2021, his most popular works were:
- Nonconvex Low-Rank Matrix Recovery with Arbitrary Outliers via Median-Truncated Gradient Descent (20 citations)
- Non-asymptotic Convergence Analysis of Two Time-scale (Natural) Actor-Critic Algorithms (16 citations)
- Reanalysis of Variance Reduced Temporal Difference Learning (14 citations)
In his most recent research, the most cited papers focused on:
- Statistics
- Mathematical analysis
- Computer network
The scientist’s investigation covers issues in Algorithm, Rate of convergence, Convergence, Markov process and Reinforcement learning.
His Algorithm research integrates issues from Empirical risk minimization, Data classification and Sigmoid function.
Many of his studies on Convergence apply to Computational complexity theory as well.
His Markov process study combines topics from a wide range of disciplines, such as Sampling and Stationary point.
His research in the fields of Temporal difference learning overlaps with other disciplines such as Variance reduction.
The study incorporates disciplines such as Resampling and Mathematical optimization in addition to Supervised learning.
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.
