- Home
- Top Scientists - Computer Science
- Avrim Blum

Discipline name
H-index
Citations
Publications
World Ranking
National Ranking

Computer Science
H-index
76
Citations
37,001
170
World Ranking
560
National Ranking
342

2007 - ACM Fellow For contributions to learning theory and algorithms.

1994 - Fellow of Alfred P. Sloan Foundation

- Artificial intelligence
- Machine learning
- Algorithm

The scientist’s investigation covers issues in Algorithm, Artificial intelligence, Combinatorics, Time complexity and Theoretical computer science. His Algorithm research also works with subjects such as

- Perceptron that connect with fields like Node and Linear programming,
- Computational learning theory which is related to area like Instance-based learning. His Artificial intelligence study combines topics from a wide range of disciplines, such as Machine learning and Power graph analysis.

His studies in Combinatorics integrate themes in fields like Discrete mathematics and Correlation clustering, Cluster analysis. His work deals with themes such as Concept class, Polynomial, Focus and Greedy algorithm, which intersect with Time complexity. His Theoretical computer science research is multidisciplinary, incorporating perspectives in Differential privacy and Learning theory.

- Combining labeled and unlabeled data with co-training (4384 citations)
- Selection of relevant features and examples in machine learning (2577 citations)
- Fast planning through planning graph analysis (1442 citations)

His scientific interests lie mostly in Artificial intelligence, Combinatorics, Algorithm, Machine learning and Discrete mathematics. As part of one scientific family, Avrim Blum deals mainly with the area of Artificial intelligence, narrowing it down to issues related to the Theoretical computer science, and often Differential privacy. As a member of one scientific family, Avrim Blum mostly works in the field of Combinatorics, focusing on Function and, on occasion, Mathematical optimization.

His study in Algorithm is interdisciplinary in nature, drawing from both Training set and Polynomial. His Approximation algorithm research is multidisciplinary, incorporating elements of Travelling salesman problem and Orienteering. His Computational learning theory research incorporates elements of Instance-based learning and Algorithmic learning theory.

- Artificial intelligence (24.41%)
- Combinatorics (21.36%)
- Algorithm (18.31%)

- Artificial intelligence (24.41%)
- Machine learning (17.29%)
- Combinatorics (21.36%)

His primary areas of investigation include Artificial intelligence, Machine learning, Combinatorics, Theoretical computer science and Mathematical optimization. The concepts of his Artificial intelligence study are interwoven with issues in Competition and Advice. His work on Feature and Decision tree as part of general Machine learning study is frequently linked to Lifelong learning and Order, bridging the gap between disciplines.

His studies in Combinatorics integrate themes in fields like Function, Small number, Discrete mathematics and Convex hull. The Theoretical computer science study which covers Topic model that intersects with Probability distribution. His Mathematical optimization study combines topics from a wide range of disciplines, such as Uniform convergence, Graph and Regret.

- Foundations of Data Science (120 citations)
- Commitment Without Regrets: Online Learning in Stackelberg Security Games (53 citations)
- The Ladder: A Reliable Leaderboard for Machine Learning Competitions (44 citations)

- Artificial intelligence
- Machine learning
- Algorithm

Avrim Blum mostly deals with Artificial intelligence, Graph, Odds, Discrete mathematics and Machine learning. In the subject of general Artificial intelligence, his work in Semi-supervised learning is often linked to Sample complexity, thereby combining diverse domains of study. His work carried out in the field of Graph brings together such families of science as Algorithm, Directed graph and Mathematical optimization.

The various areas that Avrim Blum examines in his Discrete mathematics study include Dimension, Combinatorics, Convex hull, Sparse approximation and Ball. His Combinatorics study combines topics in areas such as Function, Adaptive algorithm, Special case and Hausdorff distance. His study in the fields of Overfitting under the domain of Machine learning overlaps with other disciplines such as Quality.

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.

Combining labeled and unlabeled data with co-training

Avrim Blum;Tom Mitchell.

conference on learning theory **(1998)**

6007 Citations

Selection of relevant features and examples in machine learning

Avrim L. Blum;Pat Langley.

Artificial Intelligence **(1997)**

4277 Citations

Fast planning through planning graph analysis

Avrim L. Blum;Merrick L. Furst.

Artificial Intelligence **(1997)**

2836 Citations

Correlation Clustering

N. Bansal;A. Blum;S. Chawla.

Machine Learning archive **(2004)**

1358 Citations

Training a 3-Node Neural Network is NP-Complete

Avrim Blum;Ronald L. Rivest.

neural information processing systems **(1988)**

943 Citations

Learning from Labeled and Unlabeled Data using Graph Mincuts

Avrim Blum;Shuchi Chawla.

international conference on machine learning **(2001)**

894 Citations

Practical privacy: the SuLQ framework

Avrim Blum;Cynthia Dwork;Frank McSherry;Kobbi Nissim.

symposium on principles of database systems **(2005)**

769 Citations

A learning theory approach to non-interactive database privacy

Avrim Blum;Katrina Ligett;Aaron Roth.

symposium on the theory of computing **(2008)**

707 Citations

A learning theory approach to noninteractive database privacy

Avrim Blum;Katrina Ligett;Aaron Roth.

Journal of the ACM **(2013)**

670 Citations

Noise-tolerant learning, the parity problem, and the statistical query model

Avrim Blum;Adam Kalai;Hal Wasserman.

Journal of the ACM **(2003)**

627 Citations

Profile was last updated on December 6th, 2021.

Research.com Ranking is based on data retrieved from the Microsoft Academic Graph (MAG).

The ranking h-index is inferred from publications deemed to belong to the considered discipline.

If you think any of the details on this page are incorrect, let us know.

Contact us

Carnegie Mellon University

Tel Aviv University

Georgia Institute of Technology

Microsoft (United States)

Harvard University

Microsoft (United States)

University of Maryland, College Park

Carnegie Mellon University

Google (United States)

Eindhoven University of Technology

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Something went wrong. Please try again later.