Reza Bosagh Zadeh

Generalized Low Rank Models

Principal components analysis (PCA) is a well-known technique for approximating a tabular data set by a low rank matrix. Here, we extend the idea of PCA to handle arbitrary data sets consisting of numerical, Boolean, categorical, ordinal, and other data types. This framework encompasses many well-known techniques in data analysis, such as nonnegative matrix factorization, matrix completion, sparse and robust PCA, k-means, k-SVD, and maximum margin matrix factorization. The method handles heterogeneous data sets, and leads to coherent schemes for compressing, denoising, and imputing missing entries across all data types simultaneously. It also admits a number of interesting interpretations of the low rank factors, which allow clustering of examples or of features. We propose several parallel algorithms for fitting generalized low rank models, and describe implementations and numerical results.

Group Heterogeneity Increases the Risks of Large Group Size A Longitudinal Study of Productivity in Research Groups

Heterogeneous groups are valuable, but differences among members can weaken group identification. Weak group identification may be especially problematic in larger groups, which, in contrast with smaller groups, require more attention to motivating members and coordinating their tasks. We hypothesized that as groups increase in size, productivity would decrease with greater heterogeneity. We studied the longitudinal productivity of 549 research groups varying in disciplinary heterogeneity, institutional heterogeneity, and size. We examined their publication and citation productivity before their projects started and 5 to 9 years later. Larger groups were more productive than smaller groups, but their marginal productivity declined as their heterogeneity increased, either because their members belonged to more disciplines or to more institutions. These results provide evidence that group heterogeneity moderates the effects of group size, and they suggest that desirable diversity in groups may be better leveraged in smaller, more cohesive units.

Matrix Computations and Optimization in Apache Spark

We describe matrix computations available in the cluster programming framework, Apache Spark. Out of the box, Spark provides abstractions and implementations for distributed matrices and optimization routines using these matrices. When translating single-node algorithms to run on a distributed cluster, we observe that often a simple idea is enough: separating matrix operations from vector operations and shipping the matrix operations to be ran on the cluster, while keeping vector operations local to the driver. In the case of the Singular Value Decomposition, by taking this idea to an extreme, we are able to exploit the computational power of a cluster, while running code written decades ago for a single core. Another example is our Spark port of the popular TFOCS optimization package, originally built for MATLAB, which allows for solving Linear programs as well as a variety of other convex programs. We conclude with a comprehensive set of benchmarks for hardware accelerated matrix computations from the JVM, which is interesting in its own right, as many cluster programming frameworks use the JVM. The contributions described in this paper are already merged into Apache Spark and available on Spark installations by default, and commercially supported by a slew of companies which provide further services.

What's in a move?: normal disruption and a design challenge

The CHI community has led efforts to support teamwork, but has neglected team disruption, as may occur if team members relocate to another institution. We studied moves in 548 interdisciplinary research projects with 2691 researchers (PIs). Moves, and thus disruptions, were not rare, especially in large distributed projects. Overall, one-third of all projects experienced at least one member relocating but most moves reflected churn across high-ranking institutions. When collaborators moved, the project was disrupted. Our data suggest that moves exemplify normal disruptions. A design challenge is to help projects adapt to disruption.