Program

Session 1 8h30 - 10h00 8h30 - 8h40  Welcome and Introduction of keynote 8h40 - 9h40  Keynote: Ion Stoica, "Spark: Past, Present, and Future" 9h40 - 10h00  “Bridging the gap: Towards optimization across linear and relational algebra”, Andreas Kunft, Alexander Alexandrov, Asterios Katsifodimos and Volker Markl        Introduction: Jacek Sroka  Ion Stoica  Andreas Kunft nftSession 2 10h30 - 12h00 10h30 - 10h50  “Faucet: a user-level, modular technique for flow control in dataflow engines”, Andrea Lattuada, Frank McSherry and Zaheer Chothia 10h50 - 11h10  “Model-Centric Computation Abstractions in Machine Learning Applications”, Bingjing Zhang, Peng Bo and Judy Qiu 11h10 - 11h35  “DFA Minimization in Map-Reduce”, Gösta Grahne, Shahab Harrafi, Iraj Hedayati and Ali Moallemi 11h35 - 12h00  “Cross-System NoSQL Data Transformations with NotaQL”, Johannes Schildgen, Thomas Lottermann and Stefan Deßloch          Andrea Lattuada  Judy Qiu  Gösta Grahne  Johannes Schildgen Session 3 13h30 - 15h00 13h30 - 13h35  Introduction of keynote 13h35 - 14h35  Keynote: Carlos Guestrin, "Big Data, Small Cluster: Choosing 'big memory' (RAM, disks, SSDs) over big clusters" 14h35 - 15h00  “On Exploring Efficient Shuffle Design for In-Memory MapReduce”, Harunobu Daikoku, Hideyuki Kawashima and Osamu Tatebe      Carlos Guestrin  Haronubo Daikoku Session 4 15h30 - 17h00 15h30 - 15h50  “Toward Elastic Memory Management for Cloud Data Analytics”, Jingjing Wang and Magdalena Balazinska 15h50 - 16h10  “Some-Pairs Problems”, Jeffrey Ullman and Jonathan Ullman 16h10 - 16h35  “Tight Bounds on One- and Two-Pass MapReduce Algorithms for Matrix Multiplication”, Prakash Ramanan and Ashita Nagar 16h35 - 17h00  “Deterministic Load Balancing for Parallel Joins”, Paraschos Koutris and Nivetha Singara Vadivelu          Jingjing Wang  Jeffrey Ullman  Prakash Ramanan  Nivetha Singara Vadivelu