What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Statistics
His main research concerns Artificial intelligence, Machine learning, Boosting, Algorithm and AdaBoost.
Robert E. Schapire interconnects Stability, Bondareva–Shapley theorem, Query expansion and Pattern recognition in the investigation of issues within Artificial intelligence.
His study in the field of Multiclass classification and Overfitting is also linked to topics like Function, Multiple data and Gene ontology.
His Boosting research incorporates themes from Learning to rank, BrownBoost, Boosting methods for object categorization, Decision tree and Ensemble learning.
His study explores the link between BrownBoost and topics such as LPBoost that cross with problems in LogitBoost.
The Algorithm study combines topics in areas such as Expected value, Exponential function and Convex optimization.
His most cited work include:
- A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting (13428 citations)
- Maximum entropy modeling of species geographic distributions (9060 citations)
- Experiments with a new boosting algorithm (6502 citations)
What are the main themes of his work throughout his whole career to date?
Robert E. Schapire mostly deals with Artificial intelligence, Boosting, Machine learning, Algorithm and Mathematical optimization.
His Artificial intelligence research focuses on Stability and how it relates to Semi-supervised learning.
His research integrates issues of BrownBoost, Convex optimization, AdaBoost and Generalization error in his study of Boosting.
As a part of the same scientific family, he mostly works in the field of BrownBoost, focusing on LPBoost and, on occasion, LogitBoost.
His Machine learning research incorporates elements of Probabilistic logic and Regression.
His study in the field of Timed automaton also crosses realms of Function.
He most often published in these fields:
- Artificial intelligence (44.53%)
- Boosting (28.68%)
- Machine learning (27.17%)
What were the highlights of his more recent work (between 2014-2021)?
- Regret (13.58%)
- Artificial intelligence (44.53%)
- Oracle (6.79%)
In recent papers he was focusing on the following fields of study:
His scientific interests lie mostly in Regret, Artificial intelligence, Oracle, Mathematical optimization and Theoretical computer science.
His biological study spans a wide range of topics, including Machine learning and Pattern recognition.
His Machine learning course of study focuses on Regression and Leverage, Realizability and LPBoost.
The study incorporates disciplines such as Conditional probability, Boosting and Convex combination in addition to Mathematical optimization.
His research in Boosting intersects with topics in Bounded function, Residual, Residual neural network, AdaBoost and Generalization error.
His study in Theoretical computer science is interdisciplinary in nature, drawing from both State and Reinforcement learning.
Between 2014 and 2021, his most popular works were:
- Opening the black box: an open-source release of Maxent (526 citations)
- Contextual decision processes with low Bellman rank are PAC-learnable (110 citations)
- Achieving All with No Parameters: AdaNormalHedge (53 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Statistics
Robert E. Schapire mainly focuses on Regret, Artificial intelligence, Oracle, Machine learning and Algorithm.
His work carried out in the field of Regret brings together such families of science as Discrete mathematics, Open problem, Reduction, Class and Mathematical optimization.
His Artificial intelligence study frequently draws connections between adjacent fields such as Game theory.
He has researched Machine learning in several fields, including Classifier, Optimization problem, Active learning and Realizability.
His Algorithm study combines topics from a wide range of disciplines, such as Overfitting, Prior probability, Robustness and Mirror descent.
His studies in Reinforcement learning integrate themes in fields like Bellman equation, Model of computation, Theoretical computer science and Enumeration.
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.
