What is he best known for?
The fields of study he is best known for:
- Algorithm
- Polynomial
- Discrete mathematics
His primary scientific interests are in Discrete mathematics, Combinatorics, Computational learning theory, Constant and Computational complexity theory.
His work on Time complexity as part of general Discrete mathematics research is often related to Exponential growth, thus linking different fields of science.
His Combinatorics study combines topics from a wide range of disciplines, such as Stable polynomial and Matrix polynomial.
His Computational learning theory research incorporates elements of Artificial neural network, Lattice problem and Concept class.
His work deals with themes such as Boosting, Theoretical computer science, Boolean function and Regular polygon, which intersect with Computational complexity theory.
His study in Degree is interdisciplinary in nature, drawing from both Radius, Polynomial and Conjecture.
His most cited work include:
- Graph Nonisomorphism Has Subexponential Size Proofs Unless the Polynomial-Time Hierarchy Collapses (190 citations)
- Learning DNF in time 2 õ ( n 1/3 ) (185 citations)
- Learning intersections and thresholds of halfspaces (178 citations)
What are the main themes of his work throughout his whole career to date?
Adam R. Klivans mainly focuses on Discrete mathematics, Combinatorics, Polynomial, Algorithm and Time complexity.
His study in the fields of Boolean function under the domain of Discrete mathematics overlaps with other disciplines such as Gaussian.
His work carried out in the field of Combinatorics brings together such families of science as Intersection and Concept class.
His Polynomial study combines topics in areas such as Hypergraph, Algebraic number, Kernel method and Conjecture.
His Algorithm research includes elements of Theoretical computer science, Artificial neural network, Binary logarithm, Simple and Computational learning theory.
His Time complexity research is multidisciplinary, incorporating perspectives in Mathematical proof and Degree of a polynomial.
He most often published in these fields:
- Discrete mathematics (51.64%)
- Combinatorics (45.08%)
- Polynomial (31.97%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial neural network (19.67%)
- Gradient descent (9.02%)
- Gaussian (17.21%)
In recent papers he was focusing on the following fields of study:
Adam R. Klivans mostly deals with Artificial neural network, Gradient descent, Gaussian, Discrete mathematics and Distribution.
He combines subjects such as Function and Theoretical computer science with his study of Artificial neural network.
His research integrates issues of Time complexity and Algorithm in his study of Gradient descent.
His studies deal with areas such as Training set and Dimension as well as Discrete mathematics.
His Distribution research integrates issues from Linear regression, Approximation algorithm, Combinatorics, Linear equation and Fraction.
As a member of one scientific family, Adam R. Klivans mostly works in the field of Degree, focusing on Boolean function and, on occasion, Unit sphere.
Between 2018 and 2021, his most popular works were:
- List-decodable Linear Regression (25 citations)
- Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection (13 citations)
- Time/Accuracy Tradeoffs for Learning a ReLU with respect to Gaussian Marginals (13 citations)
In his most recent research, the most cited papers focused on:
- Algorithm
- Algebra
- Polynomial
Gradient descent, Gaussian, Distribution, Theoretical computer science and Initialization are his primary areas of study.
His studies link Discrete mathematics with Gradient descent.
His work in Gaussian incorporates the disciplines of Time complexity, Linear regression, Noise, Reduction and Combinatorics.
The various areas that Adam R. Klivans examines in his Time complexity study include Classifier and Artificial neural network, Sigmoid function.
In his study, which falls under the umbrella issue of Distribution, Exact algorithm, Monotone polygon, Open problem and Square is strongly linked to Approximation algorithm.
His Theoretical computer science research is multidisciplinary, relying on both Pruning, Leverage, Heuristic and Residual neural network.
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.
