V
Vahab Mirrokni
Researcher at Google
Publications - 390
Citations - 16175
Vahab Mirrokni is an academic researcher from Google. The author has contributed to research in topics: Computer science & Common value auction. The author has an hindex of 57, co-authored 346 publications receiving 14255 citations. Previous affiliations of Vahab Mirrokni include Vassar College & Microsoft.
Papers
More filters
Posted Content
Accelerating Gradient Boosting Machine
TL;DR: This work proposes Accelerated Gradient Boosting Machine (AGBM) by incorporating Nesterov's acceleration techniques into the design of GBM and derives novel computational guarantees for AGBM, which is the first GBM type of algorithm with theoretically-justified accelerated convergence rate.
Posted Content
Causal Inference with Bipartite Designs.
Nick Doudchenko,Minzhengxiong Zhang,Evgeni Drynkin,Edoardo M. Airoldi,Vahab Mirrokni,Jean Pouget-Abadie +5 more
TL;DR: The generalized propensity score literature is leveraged to show that unbiased estimates of causal effects for bipartite experiments under a standard set of assumptions can be obtained, and the construction of confidence sets with proper coverage probabilities is discussed.
Book ChapterDOI
A unified approach to congestion games and two-sided markets
TL;DR: A model in which each resource can assign priorities to the players and players with higher priorities can displace players with lower priorities is introduced, which does not only extend standard congestion games, but can also be seen as a model of two-sided markets with ties.
Posted Content
Stochastic bandits robust to adversarial corruptions
TL;DR: A new model of stochastic bandits with adversarial corruptions which aims to capture settings where most of the input follows a Stochastic pattern but some fraction of it can be adversarially changed to trick the algorithm, e.g., click fraud, fake reviews and email spam is introduced.