Computer Science Department at Tufts University
Roni Khardon is currently an associate professor in the Department of Computer Science at Tufts University. He earned a Ph.D. in Computer Science from Harvard University in 1996, and a M.Sc. and B.Sc. degrees from the Technion (Israel). Prior to moving to Tufts in 2000 he held a faculty position in the University of Edinburgh in Scotland. Khardon's interests include theoretical foundations, efficient algorithms, practical aspects and applications of machine learning, data mining and knowledge representation. More generally artificial intelligence and theoretical computer science.
Khardon is serving on the editorial board of the Machine Learning journal, served as a special issue editor for the journal Theoretical Computer Science, served as an area-chair for the International Conference on Machine Learning (ICML2005),co-chaired the program committee for the international Conference on Algorithmic Learning Theory (ALT 2001), and has served on numerous other programming committees for conferences in machine learning and AI.
CV: ronicv.pdf
Homepage: http://www.cs.tufts.edu/~roni/
Associated Publications: [+]Authors: Saket Joshi, Kristian Kersting, and Roni Khardon
In the Proceedings of the International Joint Conference on Artificial Intelligence
2009
Authors: G. Wachman, R. Khardon, P. Protopapas, and C. Alcock
Proceedings of the European Conference on Machine Learning (ECML)
2009
Authors: C. Wang, S. Joshi and R. Khardon
Journal of AI Research
Vol 31, pp431-472
2008
Authors: S. Joshi and R. Khardon
Proceedings of the International Conference on Automated Planning and Scheduling
2008
Authors: C. Wang, S. Joshi and R. Khardon
In the proceedings of the International Joint Conference on Artificial Intelligence
2007
Authors: G. Wachman and R. Khardon
In the proceedings of the International Conference on Machine Learning.
2007
Authors: M. Arias, R. Khardon and J. Maloberti
Journal of Machine Learning Research
Vol 8, pp549--587
2007
Authors: R. Khardon and G. Wachman
Journal of Machine Learning Research
Vol 8, pp227--248
2007
Authors: G. Garriga, R. Khardon and L. De Raedt
In the proceedings of the International Joint Conference on Artificial Intelligence.
2007
Authors: C. Wang and R. Khardon
In the proceedings of the Conference on Uncertainty in Artificial Intelligence
2007
Authors: Arias, M. and Khardon, R.
Machine Learning
Volume 64, pages 121-144
2006
Authors: Khardon,R., Arias, M., Servedio, R. A.
Information and Computation
vol. 204, pp. 816-834
2006
Authors: M. Arias and R. Khardon
Journal of Computer and System Sciences
Volume 72, Issue 1, Pages 72-94
2006
Authors: Khardon, R., D. Roth, R. A. Servedio
Journal of Artificial Intelligence Research
vol. 24 , pp. 341-356
2005
Authors: Khardon, R., Servedio, R.
Journal of Machine Learning Research
vol. 6 pp. 1405-1429
2005
Authors: M. Arias and R. Khardon
In The Proceedings of the International Conference on Inductive Logic Programming
pp26-42
2004
Authors: N. Abe, R. Khardon and T. Zeugmann (Editors)
Theoretical Computer Science
Volume 313, Issue 2, Pages 173-312
2004
Authors: M. Arias and R. Khardon
In the Proceedings of the International Conference on Algorithmic Learning Theory
2004
Authors: Arias, M. and Khardon, R.
International conference on Inductive Logic Programming
pp. 22-37
2003
Authors: Gunopulos, D., Khardon, R., Mannila, H., Saluja, S. , Toivonen, H., Sharma, R.S.
ACM Transactions on Database Systems
vol. 28, 2
2003
Authors: Khardon, R., Servedio, R.
International conference on Computational Learning Theory
pp. 87-101
2003
Authors: Arias, M., Khardon, R., Servedio, R.
International conference on Computational Learning Theory
pp. 537-551
2003
Authors: Khardon, R., Roth, D., Servedio, R. A.
Advances in Neural Information Processing Systems 14
pp. 423-430 MIT Press
2002
Authors: Arias, M. and Khardon, R.
Information and Computation
vol. 178, pp. 214-240
2002
Authors: N. Abe, R. Khardon and T. Zeugmann (Editors).
Springer LNAI 2225
2001
Authors: Arias, M. and Khardon, R.
International conference on Inductive Logic Programming
Springer LNAI, pages 21-39.
2000
Authors: Khardon, R.
Proceedings of the International Conference on Machine Learning
pp. 471-478
2000
Authors: Khardon, R.
Workshop Notes. Machine Intelligence 17
2000
Authors: Khardon, R.
Artificial Intelligence
vol. 113 pp. 125-148
1999
Authors: Khardon, R.
Machine Learning
vol. 37
1999
Authors: Khardon, R.
Proceedings of the Fourth European Conference on Computational Learning Theory
pp. 111-125
1999
Authors: R. Khardon and D. Roth
Machine Learning
vol. 35, 2, pp. 95-117
1999
Authors: Khardon, R.
Machine Learning
vol. 35, 1, pp. 57-90
1999
Authors: Khardon, R., Mannila, H., Roth, D.
Acta Informatica
pp. 267-286, 1999
1999
Authors: Khardon, R., D. Roth, L. G. Valiant
Proceedings of the International Joint Conference of Artificial Intelligence
pp. 911-917
1999
Authors: Khardon, R.
International conference on Computational Learning Theory
pp. 154-165
1998
1998
Authors: Aizenstein, H, Blum, A., Khardon, R., Kushilevitz, A., Pitt, L., Roth, D.
SIAM Journal of Computing
vol. 27, 6, pp. 1505-1530
1998
Authors: R. Khardon
Technical Report, TR-10-97, Harvard University
1997
Authors: Gunopulos, D., Khardon, R., Mannila, H. , Toivonen, H.
Proceedings of the symposium on Principles of Database Systems
pp. 209-216
1997
Authors: R. Khardon and D. Roth
Artificial Intelligence
vol. 97
pp. 169-193
1997
Authors: R. Khardon and D. Roth
Journal of the ACM
vol. 44, 5 , pp. 697-725
1997
Authors: R. Khardon
Proceedings of the National Conference on Artificial Intelligence
1996
pp. 787-792
1996
Authors: R. Khardon and S. S. Pinter
Parallel Computing
vol. 22, pp. 555-593
1996
Authors: R. Khardon and D. Roth
Artificial Intelligence
vol. 87, 1-2, pp. 187-213
1996
Authors: R. Khardon and D. Roth
Proceedings of the International Joint Conference of Artificial Intelligence
1995
pp. 319-325
1995
Authors: R. Khardon and D. Roth
International conference on Computational Learning Theory
1995
pp. 301-310
1995
Authors: R. Khardon
Journal of Artificial Intelligence Research
vol. 3, pp. 349-372
1995
Authors: R. Khardon
Information Processing Letters
Vol 49, pp. 219-222.
1994
Authors: R. Khardon and D. Roth
Proceedings of the National Conference on Artificial Intelligence
pp. 682-687
1994
Authors: Blum, A., Khardon, R., Kushilevitz, A., Pitt, L., Roth, D.
International conference on Computational Learning Theory
1994
pp. 110-117
1994
Authors: R. Khardon and D. Roth
Proceedings of the National Conference on Artificial Intelligence
pp. 1148-1153
1994
Authors: R. Khardon and S. S. Pinter
International Conference on Parallel Processing
pp. I672-I673
1991
Current Research Topics:
Description: Kernel Methods give a generic way to apply certain learning methods (maximum margin, perceptron, nearest neighbors) to domains with any structure. The main tool is a kernel function which computes inner products in some space, which serves as a virtual representation space for examples. This amazing idea (known since 60s) is being intensively investigated in the machine learning community. Our previous work investigated the scope and limitations of using kernel methods for logic learning. This issue turns out to be tricky since there are nice kernel constructions but they do not necessarily lead to successful learning. Our current focus is on two issues: kernel learning with relational data, and identifying learning algorithms which are robust to "noise" - a small amount of wrong annotation on training data.
Description: The problem of "mining frequent patterns" is one of the most widely studied problems in data mining. Here, given a database capturing some activities (e.g. shopping lists in supermarkets) one searches for patterns of activities (e.g. sets of items bought together) which occur with sufficiently high frequency. This idea has been applied in a variety of real world problems. Our previous work developed formal complexity results for itemset mining, by showing an equivalence to some problems of learning by asking questions, and developed a new algorithm which is particularly efficient when patterns sought are large. Current work is focused on mining in relational data. For example given a set of molecules described by graphs (capturing a family of interest e.g. "high solubility", or "effective drug") one would like to find frequent substructures in this family. Our Learning to Act system includes one of the earliest implementations of relational frequent set mining.
Description: Markov decision processes give a mathematical model for agents acting in a dynamic environment. The agent's actions affect the world, it own state, and whether it is "rewarded" or not. However, the results of actions are not deterministic. In relational models, the state of the world is best described by referring to objects and relations among them. This is a very intuitive setting that matches many problems. Our main interest is in developing agents that learn to act in a useful way by utilizing various sources of information: examples from a teacher, exploration by trial and error, utilizing a model of the world etc. In previous work we have developed a theoretical model for learning from examples, developed algorithms and analyzed them, and developed a system L2Act for solving AI planning problem using this framework. Our current work is focused on developing useful knowledge representations for agents' internal representations (e.g. policies) that lead to efficient and robust learning to act.
Description:
This project focuses on finding scalable solutions for mining large amounts of noisy astronomical survey data for events or unusual objects that may lead to new scientific discoveries. This project is done in collaboration with scientists from the Harvard-Smithsonian Center for Astrophysics and the Time Series Center at Harvard University.
 |
 |
| A typical (left) and anomalous (right) Eclipsing Binary | |
Description: The goal in this project is to develop an understanding of system that learn knowledge and use it for reasoning. Most of our work dealt with
propositional logic as the underlying reasoning language. The work includes developing different representation formalisms, reasoning
algorithms that use them, and algorithms for learning such representations. Our Learning to Reason results demonstrate (in a technical sense) that it can be easier to learn in order to reason (on some things) than learn a model of the world and reason from it.
Description: We are studying problems where a machine learning system sees examples and produces hypotheses which are represented by logical formulae. This generic framework fits many applications from learning moves for Chess to identifying whether molecules will work well as drugs. Our theoretical work aims to characterize the computational complexity of these problems, i.e. how easy or hard they are to solve. Our work includes developing algorithms which are provably correct and efficient, and proving lower bounds that show limitations on the efficiency of any algorithm for such problems.
Description: We have developed a system for learning from relational data (e.g. from graphs). The system is pretty efficient, gives a non traditional type of algorithm ("bottom up") based on the theoretical results, and is a state of the art Inductive Logic Programming (ILP) system. Current work is focused on solving large scale problems involving classification of molecules.
Description: This project investigates the resource complexity of learning formulae
in propositional logic. Resources include run time as well as the
number of examples needed to learn. In models where the learner can
ask questions we measure the number of questions needed to complete
the learning task. The focus is on provably correct algorithms and
their analysis.