16:20 | 17:00
Keywords defining the session:
Takeaway points of the session:
- Probabilistic structures can support both stream processing and parallel processing.
- Scalable structures use a constant amount of space to answer queries about very large data sets.
This talk will provide intuitive visual explanations of several data structures that can be used to generate incremental, scalable, and parallel summaries of streams or very large data sets. We’ll focus on building the intuitions behind why these algorithms work so you can understand how and when to use them and so that you’ll have a head start on designing your own scalable techniques.