Challenges of Machine Learning at Scale

Graham Poulter, Google

Abstract: 

Motivated by the problem of predicting whether any given ad would be clicked in response to a query, in this introductory talk we outline the requirements and large-system design challenges that arise when designing a machine learning system that makes millions of predictions per second with low latency, learns quickly from the responses to those predictions, and maintains a consistent level of model quality over time. We present alternatives for meeting those challenges using diagrams of machine learning pipelines.

Concepts used in this talk: machine learning (classification), software pipelines, sharding and replication, map-reduce

Graham is an SRE at Google working on machine learning pipelines for ad click prediction.  

Graham Poulter, Google

Graham is an SRE at Google working on machine learning pipelines for ad click prediction.  

BibTeX
@conference {208543,
author = {Graham Poulter},
title = {Challenges of Machine Learning at Scale},
year = {2016},
address = {Dublin},
publisher = {USENIX Association},
month = jul
}

Presentation Video