Components on this page are not available in Touch UI, please switch to Classic to author. Visit go/touch-ui-hub and download the switcher to navigate between the two UIs.

IMPORTANT: INSTANCE DEPRECATION NOTICE | Legacy CQ is now locked. Content creation, editing, and modification are no longer available. This page is flagged for deprecation, and starting Q3FY24, content will no longer be accessible via the CMS. For questions or support, please contact WebTech@linkedin.com

Scaling Machine Learning talk at AISTATS

May 11, 2015

LinkedIn's engineering teams build state of the art systems and algorithms to connect the world's professionals to make them more productive and successful. Up and down the stack, from best of class distributed systems like Apache Kafka to cutting edge mobile frameworks and take-no-prisoners machine learning infrastructure, LinkedIn engineering solves some of the hardest, most rewarding problems in the industry.

My team is responsible for one of the hardest – machine learning, statistical modeling and optimization. My group heads up relevance across LinkedIn applications like feed, ads, content, people you may know, sales, jobs, higher ed (including university rankings), email optimization, and others. We also work on machine learning algorithms and offline infrastructure, consumer metrics and multi-objective optimization. So, I’m very excited to speak about building out machine learning and statistical modeling for web applications at the 18th International Conference on Artificial Intelligence and Statistics, tomorrow in San Diego. If you’re at the show, come see my talk and say hello afterward.

Scaling Machine Learning and Statistics for Web Application

Time: 8:30 am
Date: Tuesday, May 12
Place: International Ballroom at the Hilton San Diego Resort and Spa

Topic:
Abstract Scaling web applications like recommendation systems, search and computational advertising is challenging. Such systems have to make astronomical number of decisions every day on what to serve users when they are using the website and/or the mobile app. Machine learning and statistical modeling approaches that can obtain insights by continuously processing large amounts of data emitted at very high frequency by these applications have emerged as the method of choice. However, there are three challenges to scale such methods : a) scientific b) infrastructure and c) organizational. I will provide an overview of these challenges and the strategies we have adopted at LinkedIn to address those. Throughout, I will illustrate with examples from real-world applications at LinkedIn.

Topics