The big challenge of Big Data analytics arises whenever the volume, velocity, or variety of data overwhelms current processing systems and techniques, resulting in performance that falls far short of desired.  Three approaches to improving the performance by orders of magnitude are:

to scale down the amount of data processed or the resources needed to perform the processing, via data synopses, approximate query processing, or other techniques;

• to scale up the computing resources by parallelizing the processing across a large multicore node and leveraging emerging platform technologies; and/or

• to scale out the computing to a large collection of distributed nodes in a cluster, in the cloud, or at the edge where the data resides.

  This talk will highlight my two decades of research tackling all three of these approaches, discussing the key challenges, our solutions and their impact, and promising future directions.