Talk of possible interest: "Learning and Incentivizing Improvement"
|Perfect timing! Here's the announcement:|
Our next TOC4Fairness seminar is this Wednesday, Dec. 7th! We will have Saba Ahmadi from TTIC speak about Learning, Incentivizing Improvement, and Fairness in the Presence of Strategic Behavior. More information is provided below:
Time: Wednesday, Dec. 7th, 9-10 am PST, 12-1 pm EST
Meeting ID: 519 647 6830
Title: Learning, Incentivizing Improvement, and Fairness in the Presence of Strategic Behavior
Abstract: In this talk I will discuss a few lines of work involving learning, incentivizing improvement, and fairness in the presence of strategic behavior. First, we consider an online linear classification problem where agents arrive one by one and they wish to be classified as positive. They observe the current prediction rule and manipulate their features to get classified as positive if they can do so for a cost less than their value for being classified as positive. We show an algorithm that makes a bounded number of mistakes in presence of strategic agents for both \ell_2 and weighted \ell_1 manipulation costs. Next, we consider an offline model where agents can do both improvement and gaming modifications to their initial feature sets. The goal is to design classifiers that encourage agents to improve and become truly qualified. In the last piece of work, we consider some fairness objectives in a pure improvement setting.
Based on joint work with Hedyeh Beyhaghi, Avrim Blum, and Keziah Naggita.
Bio: Saba Ahmadi is a postdoc at TTIC hosted by Avrim Blum. She received her Ph.D. from the University of Maryland College Park where she was advised by Samir Khuller. During her Ph.D., she visited Northwestern University for 2 years. She is interested in the social aspects of computing, learning theory, and combinatorial optimization.
Saeed Sharifi-Malvajerdi and Juba Ziani
|עדכון אחרון ב- 5/12/2022, 21:40:48 Last updated on 5/12/2022, 21:40:48 Последняя модификация 5/12/2022, 21:40:48 تمت الحتلنة الأخيرة ب- 5/12/2022, 21:40:48|
|Hi all, this week's talk at the Technion Game Theory Seminar seems of particular interest to students interested in Incentives and Learning.|
Here's the announcement:
Our next speaker in the Game Theory seminar will be Tomer Koren from Tel Aviv University.
Title: Learning by underfitting and the power of regret minimization
Based on joint works with Idan Amir, Amit Attia, Roi Livni, Yishay Mansour, Uri Sherman and Matan Schliserman.
Abstract: In this talk, I will discuss how the game-theoretic concept of regret minimization plays a pivotal role towards generalization of modern optimization methods in machine learning. I will illustrate this through some curious theoretical results and phenomena concerning Stochastic Gradient Descent (SGD) that challenge the current conventional wisdom in machine learning. The talk will not assume any prior knowledge in machine learning and/or optimization.
Date: 23.11.2022 11:30 - 12:30.
Location: Room 424, Bloomfield building.
|פורסם ב- 20/11/2022, 10:40:07 Created on 20/11/2022, 10:40:07 Создано 20/11/2022, 10:40:07 تم النشر ب- 20/11/2022, 10:40:07|
First meeting tomorrow
|ברוכים הבאים לסמינר!|
מחר מתקיים המפגש הראשון והוא יוקדש למבוא והרצאת אורח של חוקר מהתעשייה בתחום התמריצים והלמידה (חברת אאוטבריין).
כל הפרטים כאן:
להתראות בטאוב 3! ענבל
|עדכון אחרון ב- 23/10/2022, 16:38:22 Last updated on 23/10/2022, 16:38:22 Последняя модификация 23/10/2022, 16:38:22 تمت الحتلنة الأخيرة ب- 23/10/2022, 16:38:22|