Event Agenda and Speaker info
10:45 - Registration
11:00 - Tea
11:15 - Keynote: Challenges in scaling machine learning- Shrikant Srinivas Naidu, Director, Yahoo Labs, Bangalore
Shrikant's team works on applying machine learning to solve problems related to ranking and Advertisements. Prior to joining Yahoo Research he worked at Motorola where he lead teams both in product engineering and research functions. He was a member of the Motorola Science Advisory Board and has worked in the areas of Internet routing Protocols, Mobile Internet and Mobile Application Frameworks. His current interests are in the area of Machine Learning and Systems.
11:30 - Long Term Profit-Based Server Consolidation - Varsha Apte, Faculty, Dept. of Comp. Sc & Engineering,IIT Bombay
Server Consolidation enables datacenters to utilize their computing facilities efﬁciently while minimizing operating cost, to optimize datacenter operators proﬁt. Most of existing server consolidation techniques are reactive to workload changes of virtual machines. However, in general, workload of virtual machine(s) encompassing an application follows a cyclic pattern which allows us some pro-active optimizations. Varsha would tell us how.
Varsha has been at IIT Bombay since 2002. She is an Associate Professor there. Prior to that she was in the Performance Analysis department of AT&T Labs in US. She did her PhD in Computer Science from Duke University in 1994. Her core interest and expertise is in solving performance modeling problems.
12:15 - Learnings from building a linked data store - Inder Singh, Sr. Architect and Srikanth Sundarrajan, Principal Architect from InMobi
Large scale data on consumers and their behaviour can optimally be represented through a graph structure. However analysing or querying this can be challenging due to presence of hot spots in the graph, known as super nodes. In this talk Inder and Srikanth would run us through some of the known technologies and solution for storing data as a graph and in share their experience in building a graph store using compressed bitmaps.
Inder Singh works with InMobi as a Senior Architect. He is focusing on building data platforms. He has spoken in previous #lspe-in session. Srikanth Sundarrajan works as a Principal Architect at inmobi focussing on building data platforms. He is the main brain behind Apache Falcon which has also been included in the HortonWorks Data Platform
1:00 - Lunch
2:00 - Hadoop - hands on session - Karri Reddy, Technical Lead, Yahoo with #lspe-in community volunteers Dhamodharan T, Raju Venkat, Dharmesh K, Vikas K. Bajaj
Everyone in IT industry is talking about big data and how to process it. Hadoop is probably one of the oldest and matured platform to process big data. In this session Karri and the team of #lspe-in volunteers would give an overview of Hadoop and its ecosystem. Then they would run you through a hands on workshop on how to install a single node and Hadoop cluste on your laptop and run a map reduce job on it. You need to bring in your laptop with a Ubuntu 12.04 running either on a virtualization platform like Virtualbox or as a native system. Hadoop and its dependencies would be provided during the session. If we still have time, the team is planning to cover more on hadoop ecosystem or discuss the operational challenges of scaling a Hadoop cluster.
Karri is Tech Lead at Yahoo and works for the team which manages Yahoo's Hadoop service known as the Grid.
3:45 - Open forum
4:00 onwards - Tea, snacks and networking.
Enter into the EGL park from Koramangala Indiranagar intermediate ring road. The first building on your left is the venue, Yahoo!. This is the Sunriver building. Take the first left to get into the parking lot. Ask the security for help and tell them that you have come for the LSPE event at Yahoo and they will help you park.