Learning to Cache through Predictive Execution
Caching is a popular technique for bringing data closer to applications that are geographically distributed. I will present Apollo, our system that can learn data access patterns exhibited by applications to identify results of queries that, when predictively executed, can increase cache hit ratios and improve performance.
Bio: Khuzaima Daudjee's research interests are in designing and building large-scale distributed systems with a focus on storage systems, database systems and graph processing systems. He has served on program committees of conferences such as ICDCS, VLDB, Middleware and is the recipient of a best paper award at the ACM Symposium on Cloud Computing.