June 2003 - present --
Sr. Engineering Manager Yahoo! Inc. heading the Content Analysis for Verticals group. The group's major focus is providing scalable and efficient machine learning solutions for verticals within Yahoo! Search, such as Shopping, News, Hotjobs etc. More recently in charge of behavioral targeting modeling within Strategic Data Solutions group. Please review my Cool at Yahoo! page for more information.
March 2002 - June 2003 --
Research Scientist, NEC Laboratories
America in David
Pennock's group on model-based recommender systems for ResearchIndex.
July 1998 - March 2002
- Research Assistant in the Information and Computer Science Department,
UC Irvine. Currently I work on probabilistic models for approximate
querying the large databases.
June 1999 - August 1999
- Summer Internship in the IBM Almaden Research Center, San Jose, CA.
Research and Analysis of Support Vector Machines.
September 1997 - June
1998 - Teaching Assistant in the Information and Computer Science
Department, UC Irvine. Assisted in teaching courses "Intro to
Discrete Mathematics", "Intro Algorithms and Data Structures",
"Intro to Artificial Intelligence".
June 1997 - September
1997 - Summer Internship in Siemens Corporate Research, Princeton, NJ.
Investigations on non-standard ECG signal processing techniques.
September 1996 - June
1997 - I am with the Institute for Precise Mechanics and Computer
Engineering working on an application of Neural Networks to futures market
forecasting. We created an original trading system, which was successfully
tested in real-time trades.
June 1995 - June 1997
- I am with the Institute for Nuclear Physics, Moscow State University. I
did research in two fields: detection and classification of the organic
pollution of water and analysis of neural network training algorithms.
July 1994 - December 1995-Applied neural network to the solution of the plasma equilibrium
problem, performed at Moscow State University. Comparison of my results
with results obtained in the Culham Laboratory - the leading research
organization for plasma control. The code was also tested on the real data
from Tokamak COMPASS-D.
January 1994 - June 1994
- Development of a new neural network-training algorithm based on
regularization which was stable to noise in the input data, performed at
Moscow State University.
January 1993 - December
1993 - Coexecutor of the project "Effective algorithms of neural
network training for reconstruction of the hardly identifiable objects'
parameters". In the frameworks of this project I solved an Inverse
Coefficient Heat Conduction problem and compared its solution obtained by
neural networks with conventional regularization techniques.
November 1992 - December
1992 - Investigated on the Hopfield's neural net, solved an image
recognition problem with its help.
June 1999 - M. S.
degree in Information and Computer Science from University
of California, Irvine.
GPA 4.0
June 1996 - M. S.
(honors) degree in Math and Information from Moscow State University,
Department of Computational Math and Cybernetics ("diploma with
excellence"(diploma cum laude); GPA 4.95 (out of 5.0)); passed area
exams, advanced to Ph.D. candidacy
Thesis Title: "Application of
Neural Networks to Fast Speech, OCR and Water Pollution Recognition"
June 1994 - B. S.
(honors) degree in Math and Information from Moscow State University,
Department of Computational Math and Cybernetics ("diploma with
excellence"(diploma cum laude); GPA 4.99 (out of 5.0))
Thesis Title: "Application of
Neural Networks to Solution of Inverse Problems"
PATENTS
"
Automated Collection of Human-Reviewed Data" joint with Qi Su, J. Chow and W. Baker,
filed by Yahoo! Inc., 2008.
"
Demographics from Behavior" joint with N. Rochnik, A. Gupta, P. Smyth, M. Steyvers, C. Liu,
filed by Yahoo! Inc., 2008.
"
System and Method for Providing Information Regarding a Redirection of an Internet User to a Webpage"
filed by Yahoo! Inc., 2007.
"
Attribute Extraction from Unstructured Text With Limited Training Data
" joint with Ramnath Balasubramanyan,
filed by Yahoo! Inc., 2007.
"
System for Matching Users and Transportation Providers
",
filed by Yahoo! Inc., 2006.
"
Assigning Into One Set Of Categories Information That Has Been Assigned To Other Sets of Categories
", joint with Byron Dom, Hui Han and Ramnath Balasubramanyan,
filed by Yahoo! Inc., 2006.
"
Human Responses to Requests at Web Scale
", joint with Jyh-Herng Chow and Qi Lu,
filed by Yahoo! Inc., 2006.
"
System And Method For Automatically Organizing Bookmarks Through The Use of Tag Data
", joint with Tom Chi, Eren Manavoglu, Zhichen Xu, Yun Fu and Paul Heymann,
filed by Yahoo! Inc., 2006.
"
Assigning Into One Set Of Categories Information That Has Been Assigned To Other Sets of Categories
", joint with Byron Dom, Hui Han and Ramnath Balasubramanyan,
filed by Yahoo! Inc., 2006.
"
Automatic Product Categorization
", joint with Byron Dom, Ramnath Balasubramanyan, Abhishesh Goyal and Bipin Suresh,
filed by Yahoo! Inc., 2004.
"Using
Cross-Entropy with Local Patterns to Predict Global Patterns in a
Database", joint with Heikki Mannila and Padhraic Smyth, filed by
Microsoft Research, 1999.
Q. Su, D. Pavlov, J.-H. Chow, W. Baker.
Internet-Scale Collection of Human-Reviewed Data.
Proceedings of Sixteenth World Wide Web
Conference (WWW-07)
Banff, Canada 2007. PDF.
D. Pavlov, R. Balasubramanyan, B. Dom, S. Kapur, J. Parikh.
Document preprocessing for Naive Bayes classification and clustering with mixture of multinomials.
Proceedings of Tenth ACM SIGKDD
International Conference on Knowledge Discovery and Data Mining (KDD-04)
2004. Postscript.
D. Pavlov, E. Manavoglu, D.
Pennock, C. Lee Giles. Collaborative Filtering with Maximum Entropy.
IEEE Intelligent Systems, Special Issue on Mining the Web Actionable Knowledge.
2004. Postscript.
E. Manavoglu, D.
Pavlov, C. Lee Giles. Probabilstic User Behavior Models.
Proceedings of the Third IEEE International
Conference on Data Mining (ICDM-03).MelbourneFL, 2003. PDF.
D.
Pavlov. Sequence Modeling with
Mixtures of Conditional Maximum Entropy Distributions. Proceedings of the Third IEEE International Conference on Data Mining (ICDM-03).MelbourneFL, 2003. Postscript.
D.
Pavlov, A. Popescul, D. Pennock and L. Ungar. Mixtures of Conditional
Maximum Entropy Models. Proceedings of the 2003
International Conference on Machine Learning (ICML-03).WashingtonDC, 2003. Postscript.
D. Pavlov, D. Pennock. A Maximum Entropy Approach To Collaborative
Filtering in Dynamic, Sparse, High-Dimensional Domains. In Advances
in Neural Information Processing 15 (NIPS-02). Postscript.
D.
Pavlov, P. Smyth. Adaptive Approximate Querying of Large Sparse Binary
Data Sets via Probabilistic Model Averaging.Proc. of the SIAM
International Conference on Data Mining, San Francisco, 2003. Postscript.
D. Pavlov, P. Smyth. Probabilistic Query Models
for Transaction Data.Proc. of Seventh ACM SIGKDD International Conference
on Knowledge Discovery and Data Mining (KDD-01), San
Francisco, 2001. Postscript.
D. Pavlov, H. Mannila, P. Smyth. Beyond
Independence: Probabilistic Models for Query Approximation on Binary
Transaction Data. Technical Report UCI-ICS TR-01-09,
Information and Computer Science Department, UC Irvine, January 2001
(Accepted to IEEE Transactions on Data and Knowledge Engineering). Postscript.
D. Pavlov, D. Chudova, P. Smyth. Towards Scalable
Support Vector Machines Using Squashing.Proc. of Sixth ACM SIGKDD
International Conference on Knowledge Discovery and Data Mining (KDD-00),
Boston, 2000. Postscript.
D. Pavlov, H. Mannila, P. Smyth. Probabilistic
Models for Query Approximation with Large Sparse Binary Data Sets.Proc.
of Sixteenth Conference on Uncertainty in Artificial Intelligence (UAI-00),
Stanford, 2000. Postscript.
H. Mannila, D. Pavlov, P. Smyth. Prediction with
Local Patterns Using Cross-Entropy.Proc. of Fifth ACM SIGKDD
International Conference on Knowledge Discovery and Data Mining (KDD-99),
San Diego, 1999. Gzipped
Postscript.
X. Ge, S. Gaffney, D. Pavlov, P. Smyth, Local
context matching for page replacement Technical Report UCI-ICS
99-37, Sept 1999. Gzipped
Postscript.
D. I. Chudova, S. A. Dolenko, Yu. V. Orlov, D. Yu.
Pavlov, I. G. Persiantsev. Benchmarking of Different Modifications of
the Cascade Correlation Algorithm. Proc. 3rd International
Conference on Adaptive Computing in Design and Manufacture, 1998,
pp.339-344.
Yu.V.Orlov, I.G.Persiantsev, D.I.Chudova,
D.Yu.Pavlov, S.M.Babichenko. Development of a Statistics Based System
for Fluorescent Diagnostics of Organic Pollution in Water.Proc.3rd
EARSeL Workshop on Lidar Remote Sensing of Land and Sea, 1997,
pp.157-162.
Dmitry Pavlov Application of Neural Networks to
Plasma Boundary Determination (in Russian) //Achievements of
Science and Technology. Modern Mathematics' Problems. Thematical Reviews,
1995, (translated into English in Alerton Press Inc.)
Dmitry Pavlov Neural Networks in Solution of an
Inverse Coefficient Heat Conduction Problem (in Russian). //Vestnik
Moskovskogo Universiteta, 4, 1994 (translated into English in Alerton
Press Inc.)
AWARDS (SELECTED)
July 2000 - Joseph J.
Fischer Memorial Fellowship Award.
March 1995 - June 1997
- Participation in the Samsung Software Membership Program. First prizes
for outstanding research in two student contests held in the frameworks of
the program.
1994-1996 -
Scientific Council of the Moscow State University scholarship for
excellent studies and research.
1994 - Lomonosov's
scholarship for excellent studies.
1994, 1995 - Soros
student's grants for research work.
Q. Su, D. Pavlov, J.-H. Chow, W. Baker.
Internet-Scale Collection of Human-Reviewed Data.
Proceedings of Sixteenth World Wide Web
Conference (WWW-07)