Microsoft Research Connections Blog
Next at Microsoft
Social Media Collective
Posted by Rob Knies
Distributed computing is critical for most modern, Internet-scale services, enabling high availability and the ability to scale to massive, worldwide audiences. The web as we now know it is unimaginable without advances achieved in distributed computing.It is challenging, though, to attain these capabilities while ensuring the correctness and the consistency of the shared and replicated mutable state offered by such services, because of the potential for failures of various kinds, such as server and network failures.Introducing students and researchers to such challenges is the goal of Microsoft Research India’s 2012 Summer School on Distributed Algorithms, Systems, and Programming, to be held from May 28 to June 8 in the Supercomputer Education and Research Center (SERC) Auditorium of the Indian Institute of Science, located in Bangalore.
Posted by Jennifer Chayes, Microsoft distinguished scientist and managing director of Microsoft Research New England and the newly announced Microsoft Research New York City
One of the wonderful elements of basic research is that you never know where it will take you. In this case, it’s taking me home (at least metaphorically). I was born in Manhattan, and I’ve always felt a special bond with the vibrant energy, creativity, and innovative spirit of New York City. So I’m thrilled to announce the opening of the Microsoft Research New York City lab, initially consisting of 15 extraordinary researchers, most of whom are joining us from Yahoo! Research.
I’m honored to serve as managing director of the new New York City lab, in addition to my ongoing work as managing director of Microsoft Research New England, in Cambridge, Mass. Creation of this new lab represents an incredible opportunity for Microsoft Research—enabling us to bring together the right researchers in the right location at the right time.
You might have noticed in your most recent Bing search that, these days, you often can get an answer to your query without having to click through to one of the search results.For example, I recently wondered about this year’s date for Mother’s Day in the United States. I typed “mother’s day” into Bing and was greeted with a bold line of text in the middle of the screen that read “Mother’s Day is on Sunday, May 13, 2012.” Great—just what I needed.Such assistance, though, requires manual intervention. People research and write the direct answers for such requests, and, given that the list of potential web queries is endless, there aren’t enough people to go around. Expensive human help is available for only the most popular queries. That’s what Direct Answers for Search Queries in the Long Tail aims to fix.
Posted by Frank McSherry, senior researcher at Microsoft Research Silicon Valley
Big data is pretty popular at the moment. Systems such as MapReduce, Hadoop, Dryad, and DryadLINQ have made writing and executing ad hoc big-data analyses easy. Still, there are several programming patterns such systems don't support especially well.
The two we repeatedly heard about from users are incremental and iterative computation. Users want to be able to see small changes quickly, both when starting a computation and when updating previously computed results, and users want to be able to write programs that iterate a subcomputation multiple times, perhaps until convergence.
That is where Naiad comes in.