What is he best known for?
The fields of study he is best known for:
- Algebra
- Algorithm
- Machine learning
Ankur Moitra mainly focuses on Discrete mathematics, Combinatorics, Algorithm, Polynomial and Time complexity.
His research integrates issues of Symmetric tensor, Invariants of tensors, Tensor product and Rank in his study of Discrete mathematics.
His work investigates the relationship between Combinatorics and topics such as Greedy algorithm that intersect with problems in Spanning tree.
Ankur Moitra has included themes like Dimension, Subspace topology, Unsupervised learning, Fraction and Product in his Algorithm study.
He works mostly in the field of Polynomial, limiting it down to concerns involving Mathematical optimization and, occasionally, Mixture model.
In his study, Non-negative matrix factorization is inextricably linked to Factorization, which falls within the broad field of Matrix.
His most cited work include:
- A Practical Algorithm for Topic Modeling with Provable Guarantees (258 citations)
- Computing a nonnegative matrix factorization -- provably (258 citations)
- Learning Topic Models -- Going beyond SVD (211 citations)
What are the main themes of his work throughout his whole career to date?
His primary scientific interests are in Combinatorics, Algorithm, Discrete mathematics, Polynomial and Time complexity.
His research in Combinatorics intersects with topics in Upper and lower bounds and Non-negative matrix factorization.
The study incorporates disciplines such as Dimension, Matrix, Simple, Rounding and Robustness in addition to Algorithm.
The concepts of his Discrete mathematics study are interwoven with issues in Tensor and Exponential function.
The various areas that Ankur Moitra examines in his Polynomial study include Univariate, Applied mathematics and Constant.
His studies examine the connections between Time complexity and genetics, as well as such issues in Theoretical computer science, with regards to Ranking and Complement.
He most often published in these fields:
- Combinatorics (30.72%)
- Algorithm (29.41%)
- Discrete mathematics (29.41%)
What were the highlights of his more recent work (between 2019-2021)?
- Algorithm (29.41%)
- Time complexity (14.38%)
- Applied mathematics (12.42%)
In recent papers he was focusing on the following fields of study:
Algorithm, Time complexity, Applied mathematics, Matrix and Structure are his primary areas of study.
His Algorithm research includes themes of Dimension, Fraction, Odds and Order.
His Time complexity research is multidisciplinary, incorporating perspectives in Sequence and Density estimation.
Ankur Moitra interconnects Minimax, Permutation and Rank in the investigation of issues within Matrix.
As part of one scientific family, Ankur Moitra deals mainly with the area of Structure, narrowing it down to issues related to the Discrete mathematics, and often Markov chain.
His studies deal with areas such as Polynomial and Exponential function as well as Constant.
Between 2019 and 2021, his most popular works were:
- Tensor Completion Made Practical (6 citations)
- Classification Under Misspecification: Halfspaces, Generalized Linear Models, and Connections to Evolvability. (5 citations)
- Algorithmic Foundations for the Diffraction Limit. (5 citations)
In his most recent research, the most cited papers focused on:
- Algebra
- Machine learning
- Algorithm
His main research concerns Time complexity, Heuristic, Applied mathematics, Robust statistics and Matrix.
His Time complexity study combines topics in areas such as Classifier, Generalized linear model and Small set.
His work deals with themes such as Algorithm, Point, Matrix completion and Minification, which intersect with Heuristic.
The Applied mathematics study combines topics in areas such as Logarithm, Scaling and Elliptical distribution.
His Robust statistics study combines topics from a wide range of disciplines, such as Sequence, Density estimation and Theoretical computer science.
His work carried out in the field of Matrix brings together such families of science as Degree, Distribution and Pure mathematics.
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.
