{"id":4125,"date":"2018-06-15T10:48:36","date_gmt":"2018-06-15T08:48:36","guid":{"rendered":"https:\/\/blogg.mah.se\/ts\/?p=4125"},"modified":"2018-06-15T10:48:36","modified_gmt":"2018-06-15T08:48:36","slug":"on-monday-keynote-speaker-explores-fairness-in-automated-decision-making","status":"publish","type":"post","link":"https:\/\/blogg.mah.se\/ts\/2018\/06\/15\/on-monday-keynote-speaker-explores-fairness-in-automated-decision-making\/","title":{"rendered":"On Monday: keynote speaker explores fairness in automated decision-making"},"content":{"rendered":"

$\"\"$ <\/a>All are welcome to attend the opening keynote lecture of the Scandinavian Symposium and Workshops on Algorithm Theory (SWAT)<\/a> conference, held at Malm\u00f6 University on June 18-20. Sorelle Friedler<\/a>, Assistant Professor of Computer Science at Haverford College in Pennsylvania and an Affiliate at the Data & Society Research Institute will hold a lecture titled Optimizing Society? Ensuring Fairness in Automated Decision-Making<\/em><\/a>.<\/strong><\/p>\n

When and where:
\n<\/strong>Monday June 18 at 9:00-10:00 in NI:C0E11, Niagara building ground level, Nordenski\u00f6ldsgatan 1, Malm\u00f6. The keynote lecture is open to the public. No reservation necessary.<\/p>\n

More information about the SWAT conference, including program and registration information.<\/a><\/p>\n

Link to Sorelle Friedler’s webpage<\/a><\/p>\n

Lecture abstract:<\/strong>
\nAlgorithms are increasingly used to make high-stakes decisions about people; who goes to jail, what neighborhoods police deploy to, and who should be hired for a job. But if we want these decisions to be fair, this means we must take societal notions of fairness and express them using the language of math. What is a fair decision and how can it be guaranteed?<\/p>\n

In this talk, we\u2019ll discuss recent work from the new and growing field of Fairness, Accountability, and Transparency. We will examine technical definitions of fairness and non-discrimination that have been proposed and their societal counterparts. We\u2019ll also discuss methods for ensuring that algorithms are making decisions as desired, from methods to audit black-box algorithms to white-box interpretability techniques. This important field necessitates societally informed and mathematically rigorous work; we\u2019ll discuss open problems in this light.<\/p>\n","protected":false},"excerpt":{"rendered":"