A
Alexander Peysakhovich
Researcher at Facebook
Publications - 80
Citations - 4072
Alexander Peysakhovich is an academic researcher from Facebook. The author has contributed to research in topics: Reinforcement learning & Behavioral economics. The author has an hindex of 21, co-authored 75 publications receiving 3285 citations. Previous affiliations of Alexander Peysakhovich include Yale University & Harvard University.
Papers
More filters
Proceedings Article
Consequentialist Conditional Cooperation in Social Dilemmas with Imperfect Information (Short Workshop Version).
Patent
Systems and methods for providing data analysis based on applying regression
Akos Lada,Alexander Peysakhovich +1 more
TL;DR: In this paper, a set of individual time series associated with users can be used to select a plurality of variables represented via the set of time series, including at least a first variable and a second variable, and one or more regression techniques can be applied to each of the variables.
Posted Content
An Attract-Repel Decomposition of Undirected Networks.
TL;DR: In this article, the attract-repel decomposition is proposed to measure the amount of latent homophily and heterophily in social networks and co-occurrence networks.
Patent
Content relevance in a social networking system by simulating feed ranking models
Max Christian Eulenstein,Lauren E. Scissors,Alexander Peysakhovich,Lars Backstrom,Lu Wang,Virot Chiraphadhanakul +5 more
TL;DR: In this article, a social networking system builds a quality controlled and desired population-representative pool of human raters to provide ratings on content items to improve a feed ranking model used for providing its users with more relevant content.
Patent
Systems and methods for forecasting trends
TL;DR: In this paper, a model is trained to adjust growth forecasts for a content item in response to one or more users interacting with the content item, and a determination is made that a first user has interacted with the contents item.