Munich AI Lectures start

Inaugural Lecture with Prof. Cynthia Dwork

4 May 2022
Poster Munich AI Lectures with a photo ofCynthia Dwark
Prof. Cynthia Dwork gives the Inaugural Lecture of a new series organized by several Munich research cooperatives  – the Munich AI Lectures. 

The Munich AI Lectures are a joint initiative of Munich Data Science Institute (MDSI), Center for Advanced Studies Ludwig-Maximilian-University of Munich (CAS), European Laboratory for Learning and Intelligent Systems (ELLIS Munich), and Munich Center for Machine Learning (MCML) to showcase insights and ideas from experts in the field.

On a monthly basis, top-level AI researchers give a glimpse into their work and the future of AI. The lectures consist of a short presentation followed by a Q&A to enable a lively discussion with the speakers. Each lecture lasts about one hour and will be streamed live. Recordings will be available on YouTube afterwards.

We are very happy that Prof. Cynthia Dwork from Harvard University will give the inaugural lecture on "Fairness, Randomness, and the Crystal Ball". The lecture will take place virtually on 4th May 2022 at 17:00 CET. More details can be found at Munich AI Lectures.

Fairness, Randomness, and the Crystal Ball

Prediction algorithms score individuals, or individual instances, assigning to each one a number in the range from 0 to 1. That score is often interpreted as a probability: What are the chances that this loan will be repaid? How likely is this tumor to metastasize? A key question lingers: What is the "probability" of a non-repeatable event? This is the defining problem of AI. Without a satisfactory answer, how can we even specify what we want from an ideal algorithm?

This talk will introduce ‘outcome indistinguishability’ — a desideratum with roots in computational complexity theory.  We will situate the concept within the 10-year history of the theory of algorithmic fairness,  and spell out directions for future research.

About Cynthia Dwork

Cynthia Dwork, Professor of Computer Science at Harvard, Affiliated Faculty at Harvard Law School, and Distinguished Scientist at Microsoft, is renowned for placing privacy-preserving data analysis on a mathematically rigorous foundation. She has made seminal contributions in cryptography and distributed computing, and, starting in 2010, launched the field of the theory of algorithmic fairness. A recipient of numerous awards. Dwork is a member of the US National Academy of Sciences and the US National Academy of Engineering, and is a Fellow of the American Academy of Arts and Sciences and the American Philosophical Society.