What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Statistics
The scientist’s investigation covers issues in Artificial intelligence, Algorithm, Coordinate descent, Machine learning and Robustness.
His Artificial intelligence study frequently involves adjacent topics like Pattern recognition.
He has researched Algorithm in several fields, including Stochastic gradient descent, Distributed memory and Heuristics.
His Machine learning study incorporates themes from Table and Stationary point.
His Robustness research incorporates elements of Artificial neural network, MNIST database, Contextual image classification, Upper and lower bounds and Lipschitz continuity.
His research in Linear classifier tackles topics such as Data mining which are related to areas like Sparse data sets, Logistic regression and Network representation learning.
His most cited work include:
- LIBLINEAR: A Library for Large Linear Classification (5734 citations)
- A dual coordinate descent method for large-scale linear SVM (755 citations)
- ZOO: Zeroth Order Optimization Based Black-box Attacks to Deep Neural Networks without Training Substitute Models (658 citations)
What are the main themes of his work throughout his whole career to date?
His scientific interests lie mostly in Artificial intelligence, Robustness, Algorithm, Machine learning and Artificial neural network.
His Artificial intelligence study frequently links to adjacent areas such as Pattern recognition.
In Robustness, Cho-Jui Hsieh works on issues like MNIST database, which are connected to Optimization problem and Theoretical computer science.
His work carried out in the field of Algorithm brings together such families of science as Embedding and Stochastic gradient descent.
His Machine learning research focuses on Boosting in particular.
His biological study spans a wide range of topics, including Support vector machine and Asynchronous communication.
He most often published in these fields:
- Artificial intelligence (41.67%)
- Robustness (28.99%)
- Algorithm (26.09%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (41.67%)
- Robustness (28.99%)
- Machine learning (23.55%)
In recent papers he was focusing on the following fields of study:
His primary areas of investigation include Artificial intelligence, Robustness, Machine learning, Artificial neural network and Adversarial system.
In his study, Mathematical optimization is inextricably linked to Smoothing, which falls within the broad field of Artificial intelligence.
His work deals with themes such as Transformer, MNIST database, Noise, Code and Algorithm, which intersect with Robustness.
His study in Machine learning is interdisciplinary in nature, drawing from both Limit and Influence function.
His Artificial neural network study integrates concerns from other disciplines, such as Computational complexity theory, Linear programming, Network architecture and Computer engineering.
His studies deal with areas such as Subspace topology, Optimization problem and Leverage as well as Adversarial system.
Between 2019 and 2021, his most popular works were:
- Large Batch Optimization for Deep Learning: Training BERT in 76 minutes (133 citations)
- Towards Stable and Efficient Training of Verifiably Robust Neural Networks (47 citations)
- Greedy Attack and Gumbel Attack: Generating Adversarial Examples for Discrete Data (27 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Statistics
His primary areas of study are Artificial intelligence, Robustness, Machine learning, Artificial neural network and Adversarial system.
His Artificial intelligence research is multidisciplinary, incorporating perspectives in Smoothing, Matrix decomposition and Natural language processing.
His Robustness research includes elements of Algorithm, MNIST database and Reinforcement learning.
His work on Deep learning and Collaborative filtering as part of general Machine learning study is frequently linked to Detector and Space, therefore connecting diverse disciplines of science.
His studies in Artificial neural network integrate themes in fields like Network architecture, Scale, Transformer and Flexibility.
His Adversarial system research includes themes of Theoretical computer science, Gumbel distribution and Probabilistic framework.
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.
