What is he best known for?
The fields of study he is best known for:
- Statistics
- Artificial intelligence
- Machine learning
Matrix, Combinatorics, Algorithm, Artificial intelligence and Randomized algorithm are his primary areas of study.
His Matrix study combines topics from a wide range of disciplines, such as Discrete mathematics, Generalized inverse, Gibbs sampling and Rank.
His Combinatorics study integrates concerns from other disciplines, such as Embedding, Singular value decomposition, Block matrix and Matrix multiplication.
His Algorithm research includes themes of Range, Hessian matrix and Heuristics.
His work focuses on many connections between Artificial intelligence and other disciplines, such as Machine learning, that overlap with his field of interest in Function.
He has included themes like Applied mathematics, Leverage and Random projection in his Randomized algorithm study.
His most cited work include:
- A five-site model for liquid water and the reproduction of the density anomaly by rigid, nonpolarizable potential functions (1626 citations)
- Community Structure in Large Networks: Natural Cluster Sizes and the Absence of Large Well-Defined Clusters (1384 citations)
- Statistical properties of community structure in large social and information networks (825 citations)
What are the main themes of his work throughout his whole career to date?
Michael W. Mahoney spends much of his time researching Algorithm, Matrix, Artificial intelligence, Artificial neural network and Theoretical computer science.
His studies in Algorithm integrate themes in fields like Graph, Mathematical optimization and Hessian matrix.
His Matrix study incorporates themes from Discrete mathematics, Randomized algorithm, Combinatorics, Random matrix and Rank.
His Combinatorics research integrates issues from Singular value decomposition and Matrix norm.
The Artificial intelligence study combines topics in areas such as Machine learning and Pattern recognition.
The study incorporates disciplines such as Cluster analysis and Graph in addition to Theoretical computer science.
He most often published in these fields:
- Algorithm (32.54%)
- Matrix (17.99%)
- Artificial intelligence (15.34%)
What were the highlights of his more recent work (between 2019-2021)?
- Algorithm (32.54%)
- Artificial neural network (13.23%)
- Artificial intelligence (15.34%)
In recent papers he was focusing on the following fields of study:
The scientist’s investigation covers issues in Algorithm, Artificial neural network, Artificial intelligence, Quantization and Hessian matrix.
The concepts of his Algorithm study are interwoven with issues in Normalization, Transformer, Matrix, Asymptotic distribution and Lipschitz continuity.
Particularly relevant to Numerical linear algebra is his body of work in Matrix.
His Artificial neural network study also includes
- Computation which intersects with area such as Structure and Singular value decomposition,
- Scalability that intertwine with fields like Stochastic gradient descent.
His Artificial intelligence research incorporates themes from Natural language processing, Machine learning and Pattern recognition.
His Probability distribution research focuses on Randomized algorithm and how it connects with Leverage.
Between 2019 and 2021, his most popular works were:
- Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT (89 citations)
- ZeroQ: A Novel Zero Shot Quantization Framework (48 citations)
- ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning. (18 citations)
In his most recent research, the most cited papers focused on:
- Statistics
- Artificial intelligence
- Algorithm
Michael W. Mahoney mainly investigates Algorithm, Artificial neural network, Quantization, Hessian matrix and Normalization.
His research integrates issues of Dynamical systems theory, Transformer, Embedding, Polynomial and Lipschitz continuity in his study of Algorithm.
Artificial neural network is a primary field of his research addressed under Artificial intelligence.
His research in Artificial intelligence intersects with topics in Fluid dynamics and Machine learning.
His Hessian matrix research is multidisciplinary, incorporating perspectives in Computation, Block matrix, Scaling and Variance reduction.
As a part of the same scientific study, he usually deals with the Recurrent neural network, concentrating on Nonlinear system and frequently concerns with Matrix.
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.
