ADS Drinks & Data: Deep Dive into Machine Learning

Date: Wednesday 18 October 2017

Time: 16:30-18:45

Location: Roeterseiland Campus UvA, Roetersstraat, Building C – Room C1.03

Registration: https://www.meetup.com/Amsterdam-Data-Science/events/242058454/

The ADS Meet-up offers the opportunity for researchers and business to share their knowledge and give insight on a central theme, specifically on the afternoon of Wednesday 18 October this will be on Machine Learning.

In this afternoon edition, there is also the chance to network after, with drinks and snacks provided.

***

Introduction & Chair:

16:30-17:00: Speaker 1: Zeynep Akata Assistant Professor, Informatics Institute, University of Amsterdam (UvA), Scientific Manager, Delta Lab and Senior Researcher, Max Planck Institute for Informatics, Germany

17:00-17:30: Speaker 2: Jie Tang Associate Professor, Knowledge Engineering Lab, Department of Computer Science and Technology, Tsinghua University, Beijing, China

17:30-18:00: Speaker 3: Peter Grünwald Professor – Universiteit Leiden, Scientific Staff Member, Group Leader Department of Machine Learning, Centrum Wiskunde & Informatica (CWI) Amsterdam will present on:

“Bayesian inference when the model is wrong”

Bayesian inference can behave badly if the model under consideration is wrong yet useful: the posterior may fail to concentrate even for large samples, leading to extreme overfitting in practice. We demonstrate this on a very simple regression problem. The problem goes away if we make the so-called learning rate small enough, which essentially amounts to making the prior more and the data less important. Standard Bayes sets the learning rate to 1, which can be too high under model misspecification. We introduce the safe Bayesian estimator, which learns the learning rate from the data.

It behaves essentially as well as standard Bayes if the model is correct but continues to achieve good rates with wrong models. We point out relations to the learning rate as it appears in gradient descent and methods for online convex optimization such as MetaGrad.

18:00-18:45: Drinks & snacks in the cafe of the D-Building Amsterdam Business School, UvA

***

Registration is free but please do so in advance through Meet-up

The event will be in English and is open to all

***

Amsterdam Data Science (ADS) accelerates data science research by connecting, sharing and showcasing world-class technology, expertise and talent from Amsterdam on a regional, national and international level. Our research enables business and society to better gather, store, analyse and present data in order to gain valuable insights and make informed decisions.

***

Find out more about ADS at http://amsterdamdatascience.nl