על אודות
פעילות
2K עוקבים
ניסיון חינוך
פרסומים
-
Efficient classification for metric data
https://www.cs.bgu.ac.il/~karyeh/metric-classification-ieee-arxiv.pdf
-
Minimum KL-divergence on complements of $L_1$ balls
IEEE Transactions on Information Theory
-
Active Nearest-Neighbor Learning in Metric Spaces
Journal of Machine Learning Research, 2017
-
Adaptive Metric Dimensionality Reduction
Invited to Theoretical Computer Science, 2016
-
Concentration Inequalities for Dependent Random Variables via the Martingale Method
Annals of Probability, 2008
ראו פרסוםThe martingale method is used to establish concentration inequalities for a class of dependent random sequences on a countable state space, with the constants in the inequalities expressed in terms of certain mixing coefficients. Along the way, bounds are obtained on martingale differences associated with the random sequences, which may be of independent interest. As applications of the main result, concentration inequalities are also derived for inhomogeneous Markov chains and hidden Markov…
The martingale method is used to establish concentration inequalities for a class of dependent random sequences on a countable state space, with the constants in the inequalities expressed in terms of certain mixing coefficients. Along the way, bounds are obtained on martingale differences associated with the random sequences, which may be of independent interest. As applications of the main result, concentration inequalities are also derived for inhomogeneous Markov chains and hidden Markov chains, and an extremal property associated with their martingale difference bounds is established. This work complements and generalizes certain concentration inequalities obtained by Marton and Samson, while also providing different proofs of some known results
-
Efficient Regression in Metric Spaces via Approximate Lipschitz Extension
IEEE Transactions on Information Theory, 2017
-
Exact Lower Bounds for the Agnostic Probably-Approximately-Correct (PAC) Machine Learning Model
Annals of Statistics, 2019
-
Near-optimal sample compression for nearest neighbors
IEEE Transactions on Information Theory, 2018
-
A finite sample analysis of the Naive Bayes classifier
journal of Machine Learning Research, 2015
פטנטים
-
A. Kontorovich and A. Trachtenberg. Method and system for reconciling remote data.
US US 20140222760 A1. 2014.
פרויקטים
כבוד ופרסים
-
Google award: 12000 USD unrestricted gift for “Adversarial Examples and Ways to Mitigate Them”
Google award
-
Toronto prize for excellence in research
-
-
Yahoo! Faculty Research and Engagement award, 20000 USD unrestricted gift
-
-
Distinguished Contribution Award, The 5th International Workshop on Mining and Learning with Graphs (MLG)
-
-
NIPS 2014 Outstanding Reviewer Award
-
שפות
-
Hebrew
מיומנות שפת אם או דו-לשונית
-
English
מיומנות שפת אם או דו-לשונית
-
Russian
מיומנות שפת אם או דו-לשונית