Dragos D. Margineantu

Publications

Erik Bodin, Alexandru I. Stere, Dragos D. Margineantu, Carl Henrik Ek, Henry Moss (2025):
Linear combinations of Gaussian latents in generative models: interpolation and beyond

Proceedings of the International Conference on Learning Representations, ICLR 2025.

Sampada Deglurkar, Haotian Shen, Anish Muthali, Marco Pavone, Dragos D. Margineantu, Peter Karkus, Boris Ivanovic, Claire J. Tomlin (2024):
System-Level Analysis of Module Uncertainty Quantification in the Autonomy Stack

Proceedings of the 63rd IEEE Conference on Decision and Control, CDC 2024.

Francesco Leofante, Panagiotis Kouvaros, Alessio Lomuscio, Dragos D. Margineantu, Blake Edwards, Chun Kit Chung (2023):
Verification of Semantic Key Point Detection for Aircraft Pose Estimation

Proceedings of the International Conference on Knowledge Representation, KR'23.

Denis Osipychev, Dragos D. Margineantu, Girish Chowdhary (2022):
Reinforcement Learning-Based Air Traffic Deconfliction

Proceedings of the Workshop on Reinforcement Learning for Real Life, NeurIPS 2022.

Panagiotis Kouvaros, Trent Kyono, Francesco Leofante, Alessio Lomuscio, Dragos D. Margineantu, Denis Osipychev, and Yang Zhang (2021):
Formal Analysis of Neural Network-Based Systems in the Aircraft Domain

In Marieke Huisman, Corina Pasareanu, and Naijun Zhan, editors, Formal Methods, pp. 730-740, FM 2021. Springer International Publishing.

Daniel J. Fremont, Johnathan Chiu, Dragos D. Margineantu, Denis Osipychev, Sanjit A. Seshia (2020):
Formal Analysis and Redesign of a Neural Network-Based Aircraft Taxiing System with VERIFAI

Proceedings of the International Conference on Computer Aided Verification, CAV 2020.

Mohammed Elshrif, Sanjay Chawla, Franz D. Betz, Dragos D. Margineantu (2018):
Embeddings for the Identification of Aircraft Faults

Proceedings of the International Conference on Prognostics and Health Monitoring, PHM 2018.

Tomas Singliar, Dragos D. Margineantu (2011):
Scaling up Inverse Reinforcement Learning through Instructed Feature Construction

Proceedings of the Learning Workshop, Snowbird 2011.

Stephanie Moret, William Langford, Dragos D. Margineantu (2006):
Learning to Predict Channel Stability using Biogeomorphic Features

Ecological Modelling, Vol.191, Issue 1, Elsevier, 2006.

Dragos D. Margineantu (2005):
Active Cost-Sensitive Learning

Proceedings of the International Joint Conference on Artificial Intelligence, IJCAI 2005.

Dragos Margineantu (2002):
Class Probability Estimation and Cost-Sensitive Classification Decisions

Machine Learning: ECML 2002, Proceedings of the 13th European Conference on Machine Learning, pp.270-281, ©Springer Verlag, Lecture Notes in Artificial Intelligence, 2430.
Postscript preprint.

Dragos Margineantu, Thomas G. Dietterich (2002):
Improved Class Probability Estimates from Decision Tree Models

"Nonlinear Estimation and Classification", C.Holmes ed., ©Springer Verlag, Lecture Notes in Statistics.
Postscript preprint

Dragos Margineantu, Thomas G. Dietterich (2001):
Lazy Class Probability Estimators

Proceedings of the 33rd Symposium on the Interface of Computing Science and Statistics, Costa Mesa, CA.

Dragos Margineantu, Thomas G. Dietterich (2000):
Bootstrap Methods for the Cost-Sensitive Evaluation of Classifiers

Proceedings of the Seventeenth International Conference on Machine Learning (ICML-2000), pp.583-590, Morgan Kaufmann, San Francisco, CA.
Postscript preprint.

Dragos Margineantu (1999):
Building Ensembles of Classifiers for Loss Minimization

Proceedings of the 31st Symposium on the Interface: Models, Prediction, and Computing, pp.190-194.
Postscript preprint

Dragos Margineantu (1999):
Applying Supervised Learning to Real-World Problems

Proceedings of the Sixteenth National Confernce on Artificial Intelligence (AAAI-99), pp.951. Presented at the SIGART/AAAI-99 Doctoral Consortium.

Dragos Margineantu, Thomas G. Dietterich (1997):
Pruning Adaptive Boosting

Proceedings of the Fourteenth International Conference on Machine Learning (ICML-97), pp.211-218, Morgan Kaufmann, San Francisco, CA.
Postscript preprint

Daniela Crivianu-Gaita, Florin Miclea, Andrei Gaspar, Dragos Margineantu, and Stefan Holban (1997):
3D reconstruction of prostate from ultrasound images

International Journal of Medical Informatics, Vol.45, June 1997, pp.43-51, Elsevier Science.

Dragos Margineantu (1997):
Learning by using dynamic feature combination and selection

Proceedings of the IASTED/AAAI International Conference on Artificial Intelligence and Soft Computing, pp.154-156, ACTA-IASTED Press, Anaheim, CA.
Postscript preprint.

Stephane Chatre, Charles Knutson, Dragos Margineantu, Carsten Schulz-Key (1996):
Improving the DLX Performance by Taking Some of the Reduction out of RISC

Proceedings of the International Conference on Technical Informatics (ConTI-96), Timisoara, Romania.

Florin Miclea, Stefan Holban, Andrei Gaspar, Daniela Crivianu-Gaita, Dragos Margineantu (1995):
Modeling and Volume Determination of the Prostate

Proceedings of the Symposium on Automatic Control and Computer Science (SACCS-95), Iasi, Romania.

Dissertation

Dragos Margineantu (2001):
Methods for Cost-Sensitive Learning

Oregon State University, Department of Computer Science (Technical Report)
Postscript preprint

Unrefereed Publications

Dragos Margineantu (2000):
On Class Probability Estimates and Cost-Sensitive Evaluation of Classifiers

Workshop on Cost-Sensitive Learning, The Seventeenth International Conference on Machine Learning (ICML-2000).

Dragos Margineantu (2000):
When Does Imbalanced Data Require more than Cost-Sensitive Learning?

Workshop on Learning from Imbalanced Data, National Conference on Artificial Intelligence (AAAI-2000)

Dragos Margineantu, Thomas G. Dietterich (1999):
Learning Decision Trees for Loss Minimization in Multi-Class Problems

Technical Report 99-30-03, Department of Computer Science, Oregon State University

Dragos Margineantu, Julianne Monell (1996):
The equivalence of Post systems and Turing machines

Technical Report, Oregon State University

Invited Presentations

Dragos Margineantu (2001):
Learning Ensembles for Probability Estimation and Ranking

Annual Conference of the Institute for Operations Research and Management Sciences (INFORMS), November 2001

Dragos Margineantu (1998):
Issues in Applying Divide-and-Conquer Methods for Learning Real-World Problems

Neural Information Processing Systems 1998 (NIPS-98), workshop on "Learning from Ambiguous and Complex Examples"

  • LinkedIn
  • Twitter
  • Facebook
  • Instagram
  • Email

© 2019 Dragos D. Margineantu. Design: HTML5 UP.