Aryeh (Leonid) Kontorovich
Assistant professor
Ben-Gurion University
Computer Science Department
My main areas of interest are probability theory and statistics, machine learning, and
automata theory -- as well as novel ways of combining these, and their
applications to "real-world" problems.
Contact and teaching information
Papers
D. Angluin, D. Eisenstat, L. Kontorovich, L. Reyzin Lower Bounds on Learning Random Structures with Statistical Queries. Technical report.
L. Kontorovich Statistical estimation requires unbounded memory. submitted.
L. Kontorovich and B. Nadler. Universal Kernel-Based Learning with Applications to Regular Languages. Journal of Machine Learning Research 10 (2009), pp. 997-1031.
L. Kontorovich and A. Brockwell. A Strong Law of Large Numbers for Strongly Mixing Processes. submitted.
L. Kontorovich, C.Cortes and M. Mohri. Kernel Methods for Learning Languages. Theoretical Computer Science 405 (2008), pp. 223-236.
L. Kontorovich. Obtaining Measure Concentration from Markov Contraction, manuscript
L. Kontorovich. Constructing processes with prescribed mixing coefficients , Statistics and Probability Letters 78 (2008), pp. 2910-2915.
L. Kontorovich. Measure Concentration of Strongly Mixing Processes with Applications , PhD thesis.
L. Kontorovich. A Universal
Kernel for Learning Regular Languages , published in The 5th International Workshop on Mining and
Learning with Graphs, Florence, Italy, 2007 (distinguished contribution
award)
Watch video.
C. Cortes, L. Kontorovich, and M. Mohri. Learning Languages with Rational Kernels. In Proceedings of The 20th Annual Conference on Learning Theory (COLT 2007). volume 4539 of Lecture Notes in Computer Science, pages 349-364, San Diego, California, June 2007. Springer, Heidelberg, Germany.
L. Kontorovich. A Linear Programming Inequality with Applications to Concentration of Measure , manuscript
L. Kontorovich. Metric and Mixing Sufficient Conditions for Concentration of Measure , manuscript
L. Kontorovich and K. Ramanan. Concentration Inequalities for Dependent Random Variables via the Martingale Method , Annals of Probability 2008, Vol. 36, No. 6, pp. 2126-2158.
L. Kontorovich. Measure Concentration of Markov Tree Processes, manuscript
L. Kontorovich. Measure Concentration of Hidden Markov Processes, manuscript
L. Kontorovich, J. Lafferty, D. Blei. Variational Inference and Learning for a Unified Model of Syntax, Semantics and Morphology, technical report
L. Kontorovich, C.Cortes and M. Mohri. Learning Linearly Separable Languages, ALT 2006: 288-303
L. Kontorovich, D. Ron and Y. Singer. A Markov Model for the Acquisition of Morphological Structure. Technical report: abstract, .ps, .pdf
L. Kontorovich. Uniquely Decodable n-gram Embeddings. Theoretical Computer Science, 329/1-3 pp. 271-284, 2004.
Pratt, H., Polyakov, A. and Kontorovich, L.
Evidence
for Separate Processing in the Human Brainstem of Interaural Intensity and
Temporal Disparities for Sound Lateralization.
Hearing Research, 108:1-8 (1997).
"Learning Semitic Vocalization with Hidden Markov Models" with
Daniel Lee
NIPS version (NIPS
workshop poster -- link broken, original apparently lost)
MS Word version (much
more detailed)
Utilities:
Quotes:
felix qui potuit rerum cognoscere causas (Virgil)
---
otium, Catulle, tibi molestum est
otio exsultas nimiumque gestis
otium et reges prius et beatas
perdidit urbes. (Catullus)