Brian Karrer

Data Scientist

Data Science

I’m a research scientist on the Data Science team at Facebook. I received a PhD in physics from University of Michigan and a BA in mathematics and physics from Kenyon College. My current research involves building causal models of user behavior, applying distributed optimization to improve infrastructure systems, and developing experimentation methods for networked environments.

Interests

Statistical physics, complex networks, mathematical epidemiology, causal inference, and experimental design

Google Scholar Profile
Google Scholar Profile

Latest Publications

Constrained Bayesian Optimization with Noisy Experiments

Ben Letham, Brian Karrer, Guilherme Ottoni, Eytan Bakshy

Bayesian Analysis 2018 - August 16, 2018

Social Hash Partitioner: A Scalable Distributed Hypergraph Partitioner

Igor Kabiljo, Brian Karrer, Mayank Pundir, Sergey Pupyrev, Alon Shalita

VLDB 2017 - August 28, 2017

Compressing Graphs and Indexes with Recursive Graph Bisection

Laxman Dhulipala, Igor Kabiljo, Brian Karrer, Giuseppe Ottaviano, Sergey Pupyrev, Alon Shalita

KDD - August 13, 2016

Social Hash: an Assignment Framework for Optimizing Distributed Systems Operations on Social Networks

Alon Shalita, Brian Karrer, Igor Kabiljo, Arun Sharma, Alessandro Presta, Aaron Adcock, Herald Kllapi, Michael Stumm

NSDI - March 15, 2016

Graph Cluster Randomization: Network Exposure to Multiple Universes

Johan Ugander, Brian Karrer, Lars Backstrom, Jon Kleinberg

KDD - August 11, 2013

Quantifying the Invisible Audience in Social Networks

Michael Bernstein, Eytan Bakshy, Moira Burke, Brian Karrer

ACM (CHI) - April 27, 2013

News

Efficient tuning of online systems using Bayesian optimization

September 17, 2018

Introducing Social Hash Partitioner, a scalable distributed hypergraph partitioner

August 28, 2017