SEA: Search Engines Amsterdam

This week we will have an industry talk by Steve Dodson from Prelert at Elastic and an academic talk by Artem Grotov from ILPS. Followed by drinks.

This edition of SEA will be held in SPUI25.

Programme:

16:00 – 16:30 Artem Grotov

16:30 – 17:00 Steve Dodson

17:00 – 18:00 Drinks & Snacks

Details of the talks:

Artem Grotov — Deep Counterfactual Learning

Deep learning is increasingly important for training interactive systems such as search engines and recommenders. They are applied to broad a range of tasks, including ranking, text similarity, and classification. Training neural network to perform classification requires a lot of labeled data. While collecting large supervised labeled data sets is expensive and sometimes impossible, for example for personalized tasks, there often is an abundance of logged data collected from user interactions with an existing system. This type of data is called logged bandit feedback and utilizing it is challenging because such data is noisy, biased and incomplete. We propose a learning method, Constrained Conterfactual Risk Minimisation (CCRM), based on counterfactual risk minimization of empirical Bernstein bound to tackle this problem and learn from logged bandit feedback. We evaluate CCRM on an image classification task. We find that CCRM performs well in practice and outperforms existing methods.

Artem Grotov is a PhD candidate at ILPS, UvA, supervised by Prof. Maarten de Rijke.

***

Steve Dodson — Extracting Insights from Time Series with Unsupervised Machine Learning

Details for Steve Dodson’s talk will be added soon.