Denis Nekipelov

About

Denis Nekipelov is an Associate Professor of Economics and Computer Science (by Courtesy) at the University of Virginia School of Engineering and Applied Science. He holds a Ph.D. in Economics from Duke University, earned in 2008, a Master’s degree in Economics (Cum Laude) from the New Economic School in Moscow, Russia, in 2003, and both a Master of Science and Bachelor of Science in Applied Physics and Mathematics with distinctions from the Moscow Institute of Physics and Technology, also in 2003. His research interests include computational methods of industrial organization and structural economics for big data. His work has contributed to the understanding of treatment effects from combined data, digital economy analysis, preference elicitation for sponsored search advertisers, mechanism design for data science, and properties of Laplace-type estimators. He has received awards such as the ACM EC Best Paper Award in 2015 and holds a US patent related to the analysis of sponsored search auctions.

Research topics

• Computer Science
• Computer Security
• Data Mining
• Mathematical optimization
• Statistics
• Applied mathematics
• Data science
• Econometrics
• Combinatorics
• Mathematics

Selected publications

• Balancing data privacy and usability in the federal statistical system

  Proceedings of the National Academy of Sciences · 2022 · 53 citations

  The federal statistical system is experiencing competing pressures for change. On the one hand, for confidentiality reasons, much socially valuable data currently held by federal agencies is either not made available to researchers at all or only made available under onerous conditions. On the other hand, agencies which release public databases face new challenges in protecting the privacy of the subjects in those databases, which leads them to consider releasing fewer data or masking the data i…

  PublisherOA PDFDOI

• Plug-in regularized estimation of high dimensional parameters in nonlinear semiparametric models

  2018-07-04 · 19 citations

  preprintOpen access

  We propose an l1-regularized M-estimator for a high-dimensional sparse parameter that is identified by a class of semiparametric conditional moment restrictions (CMR). We estimate the nonparametric nuisance parameter by modern machine learning methods. Plugging the first-stage estimate into the CMR, we construct the M-estimator loss function for the target parameter so that its gradient is insensitive (formally, Neyman-orthogonal) with respect to the first-stage regularization bias. As a result,…

  PublisherOA PDFDOI

• Regularised orthogonal machine learning for nonlinear semiparametric models

  Econometrics Journal · 2021 · 9 citations

  1st authorCorresponding

  Summary This paper proposes a Lasso-type estimator for a high-dimensional sparse parameter identified by a single index conditional moment restriction (CMR). In addition to this parameter, the moment function can also depend on a nuisance function, such as the propensity score or the conditional choice probability, which we estimate by modern machine learning tools. We first adjust the moment function so that the gradient of the future loss function is insensitive (formally, Neyman orthogonal) w…

  PublisherDOI

• The Role of Royalties in Resource Extraction Contracts

  Land Economics · 2018-06-28 · 9 citations

  articleOpen accessSenior author

  The manner in which governments charge mineral resource producers has been the subject of considerable debate. Income-based charges such as resource rent taxes have been advocated on the theory that royalties and other output-based charges create inefficiency by distorting production decisions. Using a principal-agent approach to resource contracts, separating asset ownership from asset use, we demonstrate that royalties can be efficient under conditions of certainty and also when there is uncer…

  PublisherOA PDFDOI

• Regularized Orthogonal Machine Learning for Nonlinear Semiparametric Models

  arXiv (Cornell University) · 2018-06-13 · 6 citations

  preprintOpen access1st authorCorresponding

  This paper proposes a Lasso-type estimator for a high-dimensional sparse parameter identified by a single index conditional moment restriction (CMR). In addition to this parameter, the moment function can also depend on a nuisance function, such as the propensity score or the conditional choice probability, which we estimate by modern machine learning tools. We first adjust the moment function so that the gradient of the future loss function is insensitive (formally, Neyman-orthogonal) with resp…

  PublisherOA PDFDOI

Recent grants

• AF: Medium: Collaborative Research: Econometric Inference and Algorithmic Learning in Games

  NSF · $446k · 2016–2023

• ICES: Large: Collaborative Research: Towards Realistic Mechanisms: statistics, inference, and approximation in simple Bayes-Nash implementation

  NSF · $138k · 2014–2016

Frequent coauthors

• Stephen Ryan

  Washington University in St. Louis

  31 shared

• Paul Novosad

  Dartmouth College

  28 shared

• Sam Asher

  Imperial College London

  27 shared

• Tatiana Komarova

  16 shared

• Vasilis Syrgkanis

  16 shared

• Jason D. Hartline

  Northwestern University

  16 shared

• Han Hong

  15 shared

• Patrick Bajari

  14 shared

Awards & honors

• H. Gregg Lewis fellowship, Duke University 2003 - 2008
• ACM EC Best Paper Award 2015
• US Patent US 2011/0313851 “A Tool for Analysis of Sponsored…

Similar researchers at University of Virginia

• Kevin Skadronh-63
• David Evansh-61
• Qizhe Caih-57