I am a data scientist and software engineer at Microsoft in Cambridge, MA, USA. Previously I was a research scientist at MediaMath and Akamai Technologies.
I did a postdoc at NEC Labs. My manager at NEC was Vladimir Vapnik. I obtained my Ph.D. from the Technion My thesis advisor was Prof. Ran El-Yaniv.
I also did M.Sc. at the School of Computer Science at Tel-Aviv University, under the supervision of Prof. Amos Fiat.

My major research interests

Statistical and computational machine learning, computational advertising, data mining, information retrieval

My papers

D. Pechyony, R. Jones, and X. Li. A Joint Optimization of Incrementality and Revenue to Satisfy both Advertiser and Publisher. WWW 2013. Poster. Full Paper


Y. Wang, R. Khardon, D. Pechyony and R. Jones. Generalization Bounds for Online Learning Algorithms with Pairwise Loss Functions. COLT 2012.


D. Pechyony, L. Shen and R. Jones. Solving Large Scale Linear SVM with Distributed Block Minimization. NIPS 2011 workshop on Big Learning: Algorithms, Systems, and Tools for Learning at Scale.


D. Pechyony and V. Vapnik. Fast Optimization Algorithms for Solving SVM+. Chapter in Statistical Learning and Data Science, 2011. Software


D. Pechyony and V. Vapnik. On the Theory of Learning with Privileged Information. NIPS 2010. Proceedings version. Full version.


D. Pechyony, R. Izmailov, A. Vashist and V. Vapnik. SMO-style Algorithms for Learning using Privileged Information . DMIN 2010. Best Academic Research Paper Award. Software


R. El-Yaniv, D. Pechyony and V. Vapnik. Large Margin vs. Large Volume in Transductive Learning. ECML 2008 and the special issue of Machine Learning Journal, 72(3):173-188, 2008.


C. Cortes, M. Mohri, D. Pechyony and A. Rastogi. Stability of Transductive Regression Algorithms. ICML 2008.


R. El-Yaniv, D. Pechyony and E. Yom-Tov. Superior Multiclass Classification Through Margin-Optimized Single Binary Problem. Pattern Recognition Letters, 29(14):1954-1959, 2008.


R. Begleiter, R. El-Yaniv and D. Pechyony. Repairing Self-Confident Active Transductive Learners using Systematic Exploration. Pattern Recognition Letters, 29(9):1245-1251, 2008.


R. El-Yaniv and D. Pechyony. Transductive Rademacher Complexity and its Applications. COLT 2007 Proceedings version. Full version, Journal of Artificial Intelligence Research, 35:193-234, 2009.
Video (from Machine Learning Summer School).


R. El-Yaniv and D. Pechyony. Stable Transductive Learning. COLT 2006. Proceedings version. Full version.


A. Fiat and D. Pechyony. Decision Trees: More Theoretical Justification for Practical Algorithms. ALT 2004. Proceedings version, Full version, .


Theory and Practice of Transductive Learning. PhD Thesis. Advisor: Prof. Ran El-Yaniv. Technion, 2008.

Decision Trees: More Theoretical Justification for Practical Algorithms. MSc Thesis. Advisor: Prof. Amos Fiat. Tel -Aviv University, 2004. 

Contact info

Email: dmpechyo at microsoft dot com, pechyony at outlook dot com

Skype: dmitry_pechyony