• Publications
  • Influence
Generative Adversarial Nets
We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and aExpand
Generative adversarial networks
Generative adversarial networks are a kind of artificial intelligence algorithm designed to solve the generative modeling problem and are among the most successful generative models (especially in terms of their ability to generate realistic high-resolution images). Expand
Inferring Graphs from Cascades: A Sparse Recovery Framework
This work provides the first algorithm which recovers the graph's edges with high probability and O(s log m) measurements, and shows that this algorithm also recovers the edge weights (the parameters of the diffusion process) and is robust in the context of approximate sparsity. Expand
Detecting Network Effects: Randomizing Over Randomized Experiments
A new experimental design is leverage for testing whether SUTVA holds, without making any assumptions on how treatment effects may spill over between the treatment and the control group, and the proposed methodology can be applied to settings in which a network is not necessarily observed but, if available, can be used in the analysis. Expand
Overcoming the Curse of Sentence Length for Neural Machine Translation using Automatic Segmentation
A way to address the issue of a significant drop in translation quality when translating long sentences by automatically segmenting an input sentence into phrases that can be easily translated by the neural network translation model. Expand
Steganography is collection of methods to hide secret information (“payload”) within non-secret information (“container”). Its counterpart, Steganalysis, is the practice of determining if a messageExpand
Optimizing Cluster-based Randomized Experiments under Monotonicity
A monotonicity condition is introduced under which a novel two-stage experimental design allows us to determine which of two cluster-based designs yields the least biased estimator. Expand
Design and Analysis of Bipartite Experiments under a Linear Exposure-Response Model
The bipartite experimental framework is a recently proposed causal setting, where a bipartite graph links two distinct types of units: units that receive treatment and units whose outcomes are ofExpand
Variance Reduction in Bipartite Experiments through Correlation Clustering
A novel clustering objective and a corresponding algorithm that partitions a bipartite graph so as to maximize the statistical power of a bipartsite experiment on that graph are introduced. Expand
Testing for arbitrary interference on experimentation platforms
An experimental design strategy for testing whether the classic assumption of no interference among users, under which the outcome of one user does not depend on the treatment assigned to other users, is rarely tenable on such platforms is introduced. Expand