What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Algorithm
- Machine learning
His primary areas of investigation include Combinatorics, Discrete mathematics, Time complexity, Algorithm and Approximation algorithm.
Combinatorics and Polynomial are frequently intertwined in his study.
His Discrete mathematics research incorporates themes from Embedding, Probabilistically checkable proof and Hardness of approximation.
Sanjeev Arora interconnects Non-negative matrix factorization and NP in the investigation of issues within Time complexity.
The Approximation algorithm study combines topics in areas such as Computational complexity theory and Norm.
He has researched Computational complexity theory in several fields, including Computational geometry, Algorithmics and Theoretical computer science.
His most cited work include:
- Computational Complexity: A Modern Approach (1965 citations)
- Proof verification and the hardness of approximation problems (1121 citations)
- Probabilistic checking of proofs: a new characterization of NP (962 citations)
What are the main themes of his work throughout his whole career to date?
Sanjeev Arora focuses on Discrete mathematics, Combinatorics, Artificial intelligence, Approximation algorithm and Algorithm.
His study in Discrete mathematics is interdisciplinary in nature, drawing from both Computational complexity theory, PCP theorem, Optimization problem and Hardness of approximation.
His research investigates the link between Computational complexity theory and topics such as Algorithmics that cross with problems in Symbolic computation.
His work in Combinatorics tackles topics such as Polynomial which are related to areas like Degree.
Sanjeev Arora works mostly in the field of Artificial intelligence, limiting it down to topics relating to Natural language processing and, in certain cases, Word2vec and Embedding.
In his research, Steiner tree problem is intimately related to Travelling salesman problem, which falls under the overarching field of Approximation algorithm.
He most often published in these fields:
- Discrete mathematics (33.33%)
- Combinatorics (29.63%)
- Artificial intelligence (19.34%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (19.34%)
- Artificial neural network (9.88%)
- Deep learning (6.58%)
In recent papers he was focusing on the following fields of study:
The scientist’s investigation covers issues in Artificial intelligence, Artificial neural network, Deep learning, Algorithm and Gradient descent.
As a member of one scientific family, Sanjeev Arora mostly works in the field of Artificial intelligence, focusing on Natural language processing and, on occasion, Class and Algebraic structure.
His studies in Artificial neural network integrate themes in fields like Kernel regression, Contextual image classification and Data mining.
His Deep learning research includes elements of Discrete mathematics, Normalization, Linear regression, Mathematics education and Applied mathematics.
In his works, Sanjeev Arora undertakes multidisciplinary study on Algorithm and Generalization.
His Gradient descent research is multidisciplinary, relying on both Speedup, Mathematical optimization, Kernel and Preconditioner.
Between 2017 and 2021, his most popular works were:
- Stronger generalization bounds for deep nets via a compression approach (236 citations)
- On Exact Computation with an Infinitely Wide Neural Net (234 citations)
- Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks (218 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Algorithm
- Machine learning
Sanjeev Arora mainly focuses on Artificial neural network, Gradient descent, Artificial intelligence, Algorithm and Generalization.
The study incorporates disciplines such as Convergence and Applied mathematics in addition to Gradient descent.
Sanjeev Arora is interested in Deep learning, which is a field of Artificial intelligence.
His studies deal with areas such as Speedup, Mathematical optimization, Linear regression and Preconditioner as well as Deep learning.
His Algorithm research is multidisciplinary, incorporating elements of Kernel regression, Kernel, Small data, Simple and Compression.
His research in Natural language processing intersects with topics in Feature, Word, Word2vec and Feature 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.
