Corporate Talk


Pavel Dmitriev

(Vice President of Data Science, Outreach)

Bio: Pavel Dmitriev is a Vice President of Data Science at Outreach - the leading engagement and intelligence platform, where he works on enabling data driven decision making in Sales through experimentation and machine learning. He was previously a Principal Data Scientist with Microsoft's Analysis and Experimentation team, where he worked on scaling experimentation in Bing, Skype, and Windows OS. His work was presented at a number of international conferences such as KDD, ICSE, WWW, CIKM, BigData, and SEAA. Pavel received a Ph.D. degree in Computer Science from Cornell University and a B.S. degree in Applied Mathematics from Moscow State University.

Title for the Talk: A/B Testing A.I.

Abstract: A.I. systems are complex. They are trained on massive datasets and adapt their behavior on the fly. Their real impact on users is often unclear until the system is deployed in the real world. In this sense, the field of A.I. is similar to medicine, where the impact of a drug is not known until it is tested on real people. Yet, while in medicine FDA demands that every drug undergoes a rigorous evaluation via a randomized clinical trial, most A.I. practitioners employ very weak evaluation procedures that rely on offline metrics such as precision, recall, AUC, etc.

In this talk, I will discuss issues resulting from this lack of rigor, and show how A/B testing can help detect bias, catch performance issues, obtain deeper insights, and ensure better user experience when developing and deploying A.I. systems. I will share examples, pitfalls and lessons learned from over a decade of my experience of applying A/B testing to evaluate A.I. systems at Outreach and Microsoft. These lessons will help anyone who wants to apply A/B testing to A.I. scenarios do it correctly and maximize their learnings.

Djordje Gligorijevic

(Senior Applied Researcher, eBay)

Bio: Djordje Gligorijevic is a senior applied researcher at eBay working on a range of problems including large-scale machine learning and data mining, structured regression, extreme multi-Label classification, natural language processing, analysis of big data from heterogeneous sources, and integration of qualitative knowledge. Applications of Djordje's work span domains such as computational healthcare and medicine, computational advertising, sponsored search, and bidding landscape prediction. He received B.Sc. degree in information systems from University of Belgrade, Serbia, in 2013, and the Ph.D. degree in computer and information sciences from Temple University, Philadelphia, PA, in 2018. His professional experience also includes working as academic researcher for IQVIA and as research scientist at Yahoo! Research.

Title of Talk: Deep Learning Methods for Modeling User Behavior in Display Advertising

Abstract: Digital media companies typically collect rich data in the form of sequences of online user activities. Such data is used in various applications, involving tasks ranging from click or conversion prediction to recommendation or user segmentation. Nonetheless, each application depends upon specialized feature engineering that requires a lot of effort and typically disregards the time-varying nature of the online user behavior and heterogeneity of data collected from diverse sources. In this talk, we will discuss advances in modeling deep representations of users’ online activities through time-preserving and noise annealing techniques. These techniques, readily accessible for many problem formulations and seamlessly applicable to desired tasks, sidestep the burden of task-driven feature engineering. Conducted experiments both on public and private data show their effectiveness on a range of tasks from conversion prediction to targeting efforts within a major advertising company.

Adel Ahmadyan

(Senior Research Engineer, Google Core ML team)

Bio: Adel Ahmadyan is a senior research engineer at the Google Core ML team, where he is working on the research and development of leading on-device machine learning solutions. Adel specializes in real-time computer vision and has previously worked across the industry in computer vision teams at Google, Zillow, and Snap. He has published papers in several international conferences and journals such as CVPR, CDC, DAC, DATE, TCAD. Adel received a Ph.D. degree in Electrical and Computer Engineering from the University of Illinois at Urbana-Champaign and a B.S. and M.S. degree in Computer Engineering from Sharif University of Technology, Tehran. 

Title of Talk: On Device Machine Learning for Mobile and Web

Abstract: The compute demand for machine learning solutions is exponentially increasing as AI is becoming more ubiquitous in our daily lives. Traditionally, ML models only ran on powerful servers in the Cloud. On-device Machine Learning is when you perform inference with models directly on a device (e.g. in a mobile app or web browser). The ML model processes input data—like images, text, or audio—on device rather than sending that data to a server and doing the processing there. On Device ML has many benefits over traditional cloud AI, such as reduced compute cost, lower latency, and preserving privacy. Google provides easy-to-use turn-key solutions for running ML algorithms on devices for mobile and web. In this talk, we cover how to use and integrate on-device ML models in your app and deploy it in production.


Important Deadlines

Full Paper Submission:15th January 2023
Acceptance Notification: 1st February 2023
Final Paper Submission:15th February
Early Bird Registration: 15th February 2023
Presentation Submission: 17th February 2023
Conference: 8 - 11 March 2023

Previous Conference


Sister Conferences





Generic selectors
Exact matches only
Search in title
Search in content
Post Type Selectors


•    Best Paper Award will be given for each track
•    Conference Record No- 54503