What is he best known for?
The fields of study he is best known for:
- Algorithm
- Artificial intelligence
- Machine learning
His primary areas of investigation include Learnability, Discrete mathematics, Artificial intelligence, Convex optimization and Combinatorics.
His studies examine the connections between Learnability and genetics, as well as such issues in Boolean function, with regards to Fourier series, Bounded function, Boosting, Oracle and Decision tree.
His Discrete mathematics research incorporates themes from Upper and lower bounds and Distribution.
In his research on the topic of Upper and lower bounds, Iterative method is strongly related with Computational problem.
Within one scientific family, Vitaly Feldman focuses on topics pertaining to Machine learning under Artificial intelligence, and may sometimes address concerns connected to Generalization, Statistical inference and Differential privacy.
His Combinatorics research includes elements of Computational complexity theory and Logarithm.
His most cited work include:
- The reusable holdout: Preserving validity in adaptive data analysis (199 citations)
- Preserving Statistical Validity in Adaptive Data Analysis (191 citations)
- Cognitive computing building block: A versatile and efficient digital neuron model for neurosynaptic cores (181 citations)
What are the main themes of his work throughout his whole career to date?
Vitaly Feldman mainly focuses on Combinatorics, Discrete mathematics, Function, Upper and lower bounds and Algorithm.
His work carried out in the field of Combinatorics brings together such families of science as Distribution and Polynomial.
His study in the field of Concept class is also linked to topics like Monotone polygon.
In his research, Vitaly Feldman undertakes multidisciplinary study on Upper and lower bounds and Convex optimization.
His biological study spans a wide range of topics, including Stability, Active learning and Generalization.
The concepts of his Generalization study are interwoven with issues in Machine learning, Overfitting, Artificial intelligence and Generalization error.
He most often published in these fields:
- Combinatorics (28.57%)
- Discrete mathematics (27.98%)
- Function (24.40%)
What were the highlights of his more recent work (between 2018-2021)?
- Convex optimization (14.29%)
- Upper and lower bounds (20.24%)
- Differential privacy (13.10%)
In recent papers he was focusing on the following fields of study:
His primary scientific interests are in Convex optimization, Upper and lower bounds, Differential privacy, Stability and Artificial intelligence.
His Upper and lower bounds study incorporates themes from Discrete mathematics, Theoretical computer science and Test set.
Vitaly Feldman combines subjects such as Shuffling, Accounting method and Anonymity with his study of Differential privacy.
His research investigates the connection between Artificial intelligence and topics such as Machine learning that intersect with problems in Long tail.
His studies in Stochastic gradient descent integrate themes in fields like Algorithm and Generalization.
His Combinatorics investigation overlaps with Simple and Function.
Between 2018 and 2021, his most popular works were:
- Amplification by shuffling: from local to central differential privacy via anonymity (87 citations)
- Does learning require memorization? a short tale about a long tail (43 citations)
- Private Stochastic Convex Optimization with Optimal Rates (43 citations)
In his most recent research, the most cited papers focused on:
- Algorithm
- Mathematical analysis
- Artificial intelligence
His main research concerns Generalization, Stochastic gradient descent, Convex optimization, Applied mathematics and Range.
His study in Generalization is interdisciplinary in nature, drawing from both Machine learning, Generalization error and Artificial intelligence.
His work on Classifier, Overfitting and Image as part of general Artificial intelligence research is frequently linked to Simple, thereby connecting diverse disciplines of science.
His Convex optimization study frequently links to adjacent areas such as Convex function.
Vitaly Feldman has researched Range in several fields, including Algorithm and Market fragmentation.
His Lipschitz continuity study combines topics from a wide range of disciplines, such as Upper and lower bounds and Logarithm.
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.
