Explore the latest research from Facebook

All Publications

August 31, 2021 Ilyes Khemakhem, Ricardo P. Monti, Robert Leech, Aapo Hyvärinen
Paper

Causal Autoregressive Flows

In this work, we highlight an intrinsic correspondence between a simple family of autoregressive normalizing flows and identifiable causal models. We exploit the fact that autoregressive flow architectures define an ordering over variables, analogous to a causal ordering, to show that they are well-suited to performing a range of causal inference tasks, ranging from causal discovery to making interventional and counterfactual predictions.
Paper
August 19, 2021 Brian Karrer, Liang Shi, Monica Bhole, Matt Goldman, Tyrone Palmer, Charlie Gelman, Mikael Konutgan, Feng Sun
Paper

Network Experimentation at Scale

In our estimation procedure, we introduce a cluster-based regression adjustment that substantially improves precision for estimating global treatment effects, as well as a procedure to test for interference. With our regression adjustment, we find that imbalanced clusters can better account for interference than balanced clusters without sacrificing accuracy.
Paper
August 14, 2021 Martin Valdez-Vivas, Varun Sharma, Nick Stanisha, Shan Li, Luo Mi, Wei Jiang, Alex Kalinin, Josh Metzler
Paper

Clockwork: a Delay-Based Global Scheduling Framework for More Consistent Landing Times in the Data Warehouse

We present Clockwork, a delay-based global scheduling framework for data pipelines which improves landing time stability by spreading out tasks throughout the day.
Paper
August 13, 2021 Dimitris Kalimeris, Smriti Bhagat, Shankar Kalyanaraman, Udi Weinsberg
Paper

Preference Amplification in Recommender Systems

We propose a theoretical framework for studying such amplification in a matrix factorization based recommender system. We model the dynamics of the system, where users interact with the recommender systems and gradually “drift” toward the recommended content, with the recommender system adapting, based on user feedback, to the updated preferences.
Paper
July 22, 2021 Da Li, Robert Pyke, Runchao Jiang
Paper

A Scalable Cloud-based Architecture to Deploy JupyterHub for Computational Social Science Research

This paper describes a scalable solution to deploy JupyterHub for computational social science research on the cloud. We use a reference architecture on AWS to walk through the design principles and details.
Paper
July 19, 2021 Mark Tygert
Paper

Cumulative deviation of a subpopulation from the full population

The cumulative approach avoids binning that smooths over deviations of the subpopulation from the full population. Such cumulative aggregation furnishes both high-resolution graphical methods and simple scalar summary statistics (analogous to those of Kuiper and of Kolmogorov and Smirnov used in statistical significance testing for comparing probability distributions).
Paper
July 18, 2021 Arun Kumar Kuchibhotla, Qinqing Zheng
Paper

Near-Optimal Confidence Sequences for Bounded Random Variables

We show that it improves on the existing approaches that use the Cramer-Chernoff technique such as the Hoeffding, Bernstein, and Bennett inequalities. The resulting confidence sequence is confirmed to be favorable in synthetic coverage problems, adaptive stopping algorithms, and multi-armed bandit problems.
Paper
July 11, 2021 Viet Ha-Thuc, Matthew Wood, Yunli Liu, Jagadeesan Sundaresan
Paper

From Producer Success to Retention: a New Role of Search and Recommendation Systems on Marketplaces

In this talk, we discuss how these systems will need to evolve from the traditional formulations by incorporating the producer value into their objectives. Jointly optimizing the ranking functions behind these systems on both consumer and producer values is a new direction and raises many technical challenges.
Paper
July 1, 2021 Vincent Conitzer, Christian Kroer, Eric Sodomka, Nicolas E. Stier-Moses
Paper

Multiplicative Pacing Equilibria in Auction Markets

Motivated by a mechanism used in practice by several companies, this paper considers a smoothing procedure that relies on pacing multipliers: on behalf of each buyer, the auction market applies a factor between 0 and 1 that uniformly scales the bids across all auctions.
Paper
July 1, 2021 Michael Bailey, Patrick Farrell, Theresa Kuchler, Johannes Stroebel
Paper

Social Connectedness in Urban Areas

We use anonymized and aggregated data from Facebook to explore the spatial structure of social networks in the New York metro area. We find that a substantial share of urban residents’ connections are to individuals who are located nearby.
Paper