What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Statistics
His primary scientific interests are in Mathematical optimization, Artificial intelligence, Algorithm, Machine learning and Support vector machine.
The concepts of his Mathematical optimization study are interwoven with issues in Linear prediction and Stochastic gradient descent.
His Artificial intelligence study combines topics in areas such as Coding, Data mining and Pattern recognition.
His Algorithm research is multidisciplinary, relying on both Regular polygon, Hidden semi-Markov model, Forward algorithm, Markov model and Eigenvalues and eigenvectors.
His work carried out in the field of Machine learning brings together such families of science as Training set and Search engine.
His study in Support vector machine is interdisciplinary in nature, drawing from both Logistic regression and Convex optimization.
His most cited work include:
- Accelerating Stochastic Gradient Descent using Predictive Variance Reduction (1536 citations)
- A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data (1197 citations)
- Solving large scale linear prediction problems using stochastic gradient descent algorithms (832 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of investigation include Artificial intelligence, Mathematical optimization, Algorithm, Machine learning and Applied mathematics.
His research in Artificial intelligence tackles topics such as Pattern recognition which are related to areas like Image.
His Mathematical optimization research focuses on Rate of convergence and how it relates to Gradient descent.
His research integrates issues of Matrix, Regular polygon, Graphical model, Sequence and Eigenvalues and eigenvectors in his study of Algorithm.
His research in Machine learning is mostly concerned with Semi-supervised learning.
His Applied mathematics research incorporates elements of Convergence, Stationary point and Regularization.
He most often published in these fields:
- Artificial intelligence (36.82%)
- Mathematical optimization (25.05%)
- Algorithm (23.31%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (36.82%)
- Machine learning (16.34%)
- Artificial neural network (7.63%)
In recent papers he was focusing on the following fields of study:
Tong Zhang mainly focuses on Artificial intelligence, Machine learning, Artificial neural network, Algorithm and Pattern recognition.
He merges Artificial intelligence with Architecture in his research.
His Machine learning research includes themes of Adversarial system, Sample and Bayesian probability.
His Algorithm research is multidisciplinary, incorporating elements of Transformer, Matrix, Representation, Rate of convergence and Machine translation.
Tong Zhang regularly ties together related areas like Mathematical optimization in his Reinforcement learning studies.
In the subject of general Mathematical optimization, his work in Empirical risk minimization is often linked to Primal dual, thereby combining diverse domains of study.
Between 2018 and 2021, his most popular works were:
- UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders (68 citations)
- Efficient Decision-Based Black-Box Adversarial Attacks on Face Recognition (66 citations)
- DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression (47 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Statistics
- Machine learning
Tong Zhang spends much of his time researching Artificial intelligence, Machine learning, Artificial neural network, Stochastic gradient descent and Pattern recognition.
His work in Artificial intelligence is not limited to one particular discipline; it also encompasses Natural language processing.
The study incorporates disciplines such as Adversarial system, Sample and Bayesian probability in addition to Machine learning.
His study in the field of Deep neural networks is also linked to topics like Architecture.
Tong Zhang combines subjects such as Regularization, Quadratic equation, Saddle point and Compression with his study of Stochastic gradient descent.
His study explores the link between Pattern recognition and topics such as Data point that cross with problems in Subspace clustering, Classifier, Contrast and Classifier.
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.
