Research
We provide tight upper and lower bounds on the complexity of minimizing the average of $m$ convex functions using gradient and prox information for the component functions. We show a significant gap between the complexity…
We’re excited to have been part of ACM MobiCom 2016, the Annual International Conference on Mobile Computing and Networking in NYC on October 3-7, 2016. The conference serves as the premier international forum addressing networks,…
Our society has entered a data-driven era, in which not only enormous amounts of data are being generated every day, but there are also growing expectations placed on their analysis. Exploring these massive and complex…
Universal Dependencies offer a homogeneous syntactic representation across languages fostering multilingual NLP research. However, dependency structures lack a transparent syntax-semantics interface like CCG, making it hard to derive target-application specific semantics in a synchronous compositional…
The presentation slide and the complete schedule of Dr. TLA+ Series are available at https://github.com/tlaplus/DrTLAPlus. Replicating data across geographically distributed data centers is the new norm in cloud services. Compared to Classic Paxos, Fast Paxos shines…
By John Kaiser, Writer, Microsoft Research Microsoft Research hosted its third annual Data Science Summer School in New York City as a diverse group of undergraduate students deployed some of the latest data crunching techniques…
Several important applications require completion a low-rank matrix in presence of gross outliers. Examples include robust PCA with missing entries, robust recommendation system, foreground background separation in sublinear time etc. Existing solutions for this problem…
