Thomas G. Dietterich

35.3k total citations · 4 hit papers
167 papers, 15.3k citations indexed

About

Thomas G. Dietterich is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Computer Networks and Communications. According to data from OpenAlex, Thomas G. Dietterich has authored 167 papers receiving a total of 15.3k indexed citations (citations by other indexed papers that have themselves been cited), including 101 papers in Artificial Intelligence, 27 papers in Computer Vision and Pattern Recognition and 15 papers in Computer Networks and Communications. Recurrent topics in Thomas G. Dietterich's work include Machine Learning and Algorithms (24 papers), Machine Learning and Data Classification (21 papers) and Reinforcement Learning in Robotics (17 papers). Thomas G. Dietterich is often cited by papers focused on Machine Learning and Algorithms (24 papers), Machine Learning and Data Classification (21 papers) and Reinforcement Learning in Robotics (17 papers). Thomas G. Dietterich collaborates with scholars based in United States, Australia and Germany. Thomas G. Dietterich's co-authors include Richard H. Lathrop, Tomás Lozano‐Pérez, Todd K. Leen, Volker Tresp, Hussein Almuallim, Dragos D. Margineantu, Ryszard S. Michalski, Dietrich Wettschereck, Wei Zhang and Giorgio Valentini and has published in prestigious journals such as Communications of the ACM, Ecological Economics and Pattern Recognition.

In The Last Decade

Thomas G. Dietterich

164 papers receiving 14.1k citations

Hit Papers

Approximate Statistical Tests for Comparing Supervised Cl... 1997 2026 2006 2016 1998 2000 1997 2000 500 1000 1.5k 2.0k

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name h Career Trend Papers Cites
Thomas G. Dietterich United States 48 8.5k 3.9k 1.8k 1.1k 1.1k 167 15.3k
Ludmila I. Kuncheva United Kingdom 45 7.5k 0.9× 3.6k 0.9× 1.3k 0.7× 892 0.8× 1.4k 1.2× 128 12.3k
Krzysztof J. Cios United States 29 6.3k 0.7× 3.7k 0.9× 1.3k 0.7× 1.1k 0.9× 1.2k 1.1× 128 14.8k
Peter Flach United Kingdom 45 9.5k 1.1× 6.1k 1.6× 1.9k 1.1× 1.3k 1.2× 1.4k 1.2× 218 20.9k
M. Narasimha Murty India 23 6.2k 0.7× 3.1k 0.8× 2.0k 1.1× 810 0.7× 2.0k 1.7× 121 11.5k
Sameer Singh United States 48 13.4k 1.6× 3.3k 0.8× 1.4k 0.8× 723 0.6× 1.1k 1.0× 255 20.2k
Tom Fawcett United States 24 7.1k 0.8× 2.2k 0.6× 2.4k 1.4× 1.0k 0.9× 1.4k 1.2× 38 20.2k
Olivier Chapelle United States 45 7.7k 0.9× 5.5k 1.4× 2.1k 1.2× 545 0.5× 1.1k 1.0× 89 14.1k
Rich Caruana United States 40 8.5k 1.0× 3.1k 0.8× 1.6k 0.9× 536 0.5× 1.0k 0.9× 104 15.4k
John Langford United States 37 7.2k 0.8× 6.0k 1.5× 1.3k 0.7× 894 0.8× 1.8k 1.6× 115 15.1k
Janez Demšar Slovenia 25 6.6k 0.8× 2.3k 0.6× 1.6k 0.9× 1.2k 1.0× 972 0.9× 54 11.4k

Countries citing papers authored by Thomas G. Dietterich

Since Specialization
Citations

This map shows the geographic impact of Thomas G. Dietterich's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Thomas G. Dietterich with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Thomas G. Dietterich more than expected).

Fields of papers citing papers by Thomas G. Dietterich

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Thomas G. Dietterich. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Thomas G. Dietterich. The network helps show where Thomas G. Dietterich may publish in the future.

Co-authorship network of co-authors of Thomas G. Dietterich

This figure shows the co-authorship network connecting the top 25 collaborators of Thomas G. Dietterich. A scholar is included among the top collaborators of Thomas G. Dietterich based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Thomas G. Dietterich. Thomas G. Dietterich is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

20 of 20 papers shown
1.
Dietterich, Thomas G.. (2025). Learning and Reasoning. Lecture notes in computer science.
2.
Dietterich, Thomas G., et al.. (2018). Efficient Exploration for Constrained MDPs.. National Conference on Artificial Intelligence. 2 indexed citations
3.
Fern, Alan, et al.. (2014). Active lmitation learning: formal and practical reductions to I.I.D. learning. Journal of Machine Learning Research. 15(1). 3925–3963. 10 indexed citations
4.
Dietterich, Thomas G., et al.. (2008). Integrating multiple learning components through Markov logic. National Conference on Artificial Intelligence. 622–627. 4 indexed citations
5.
Paasch, Robert, et al.. (2007). Product Innovation for Interdisciplinary Design Under Changing Requirements. Guidelines for a Decision Support Method Adapted to NPD Processes. 10 indexed citations
6.
Shen, Jianqiang, Lida Li, & Thomas G. Dietterich. (2007). Real-time detection of task switches of desktop users. International Joint Conference on Artificial Intelligence. 2868–2873. 23 indexed citations
7.
Stumpf, Simone, Margaret Burnett, & Thomas G. Dietterich. (2007). Improving Intelligent Assistants for Desktop Activities.. ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam). 119–121. 2 indexed citations
8.
Dietterich, Thomas G., et al.. (2003). Model-based policy gradient reinforcement learning. International Conference on Machine Learning. 776–783. 12 indexed citations
9.
Valentini, Giorgio & Thomas G. Dietterich. (2003). Low bias bagged support vector machines. International Conference on Machine Learning. 752–759. 46 indexed citations
10.
Dietterich, Thomas G., et al.. (2001). Stabilizing Value Function Approximation with the BFBP Algorithm. Neural Information Processing Systems. 14. 1587–1594. 2 indexed citations
11.
Chown, Eric & Thomas G. Dietterich. (2000). A Divide and Conquer Approach to Learning from Prior Knowledge. International Conference on Machine Learning. 143–150. 4 indexed citations
12.
Margineantu, Dragos D. & Thomas G. Dietterich. (1997). Pruning Adaptive Boosting. International Conference on Machine Learning. 211–218. 360 indexed citations
13.
Shavlik, Jude, et al.. (1991). Readings in Machine Learning. Morgan Kaufmann Publishers Inc. eBooks. 239 indexed citations
14.
Almuallim, Hussein & Thomas G. Dietterich. (1991). Learning with many irrelevant features. National Conference on Artificial Intelligence. 27(12). 547–552. 403 indexed citations
15.
Goel, Ashok K., et al.. (1991). Knowledge Compilation: A Symposium. IEEE Intelligent Systems. 6(2). 71–93. 17 indexed citations
16.
Wettschereck, Dietrich & Thomas G. Dietterich. (1991). Improving the Performance of Radial Basis Function Networks by Learning Center Locations. Neural Information Processing Systems. 4. 1133–1140. 103 indexed citations
17.
Flann, Nicholas S., et al.. (1988). An efficient ATMS for equivalence relations. National Conference on Artificial Intelligence. 182–187. 2 indexed citations
18.
Flann, Nicholas S., et al.. (1987). Forward chaining logic programming with the ATMS. National Conference on Artificial Intelligence. 24–29. 3 indexed citations
19.
Flann, Nicholas S. & Thomas G. Dietterich. (1986). Selecting appropriate representations for learning from examples. National Conference on Artificial Intelligence. 460–466. 28 indexed citations
20.
Dietterich, Thomas G.. (1980). Applying general induction methods to the card game eleusis. National Conference on Artificial Intelligence. 46(22). 218–220. 11 indexed citations

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact

Rankless by CCL
2026