November 2024 - Ml-reading-group - lists.saarland-informatics-campus.de

Guest talk by Amin Charusaie (MPI-IS) on Dec 3rd at 10:30am
by Krikamol Muandet 03 Dec '24

03 Dec '24

Dear all, Amin Charusaie (https://charusaie.github.io/) from Max Planck Institute for Intelligent Systems (MPI-IS) will visit us during Dec 2-3 and will talk about his research. You are cordially invited to attend the talk. Please feel free to forward this information to anyone who might be interested. Title: Optimal Multi-Objective Learn-to-Defer: Possibility, Complexity, and a Post-Processing Framework Location: Seminar room 1.01, CISPA D2 Date/Time: Tuesday, December 3rd at 10:30am Abstract: Learn-to-Defer (L2D) is a paradigm that enables learning algorithms to work not in isolation but as a team with human experts. In this paradigm, we permit the system to defer a subset of its tasks to the expert. Although there are currently systems that follow this paradigm and are designed to optimize the accuracy of the final human-AI team, the general methodology for developing such systems under a set of constraints (e.g., algorithmic fairness, expert intervention budget, defer of anomaly, etc.) remains largely unexplored. In this presentation, I discuss the complexity of obtaining an optimal deterministic solution to multi-objective L2D, possibility of learning deferral labels, and achieve the optimal random solution via a d-dimensional generalization to the fundamental lemma of Neyman and Pearson. I further discuss the implications of such generalization to a variety of multi-objective learning problems beyond L2D. Finally, I provide experimental results that show the effectiveness of the introduced method on a series of L2D datasets. If you would like to meet him either in person or virtually, please contact me via muandet(a)cispa.de. Best, Krikamol --- Krikamol Muandet, Dr. rer. nat. | Tenure-Track Faculty CISPA — Helmholtz Center for Information Security Stuhlsatzenhaus 5, 66123 Saarbrücken, Germany +49 681 87083 2558 | muandet(a)cispa.de | https://krikamol.org

1 3

Reading Group - Nov 27th
by kalampalikis 26 Nov '24

26 Nov '24

Dear all, I hope this email finds you well. For the next reading group (Wednesday, November 27th) we will have *Kavya* continue our Decision Making series and she will present the paper: "A Justice-Based Framework for the Analysis of Algorithmic Fairness-Utility Trade-Offs". As always, the reading group will take place from *14:30* to max 16:00. For those physically in the UdS campus, the session will be hosted as usual in *room 0.01 of the E.1.7 building*. For those attending remotely, we will set up the Zoom session for which you can find a link in the google sheet. Please let me know if I missed something. Otherwise, I'll see you soon! Cheers, Nektarios

1 0

Decision making series videos and slides
by Isabel Valera 20 Nov '24

20 Nov '24

Dear all, Please find in the following link <https://unisaarlandde-my.sharepoint.com/:f:/g/personal/isva001_uni-saarland…> the videos of the Decision Making Series. The link will expire on December 20 and does not allow for downloading, so please watch before. I will add the last one as well. For the speakers, could you please share the slides as well? Thanks, Isabel

2 1

CISPA's Distinguished Lecture Series - How to make machines that adapt quickly - Emtiyaz Khan - 15.11.2024 at 15:00
by Huynh Quang Kiet Vo 14 Nov '24

14 Nov '24

Dear all, On Friday (15.11.2024) at 15:00, Emtiyaz Khan will give a a talk at CISPA (https://cispa.de/en/dls-khan). As the talk is open to the public and might be relevant to our research, everyone is welcome to join. Best Regards, Kiet Vo

2 1

- Stackelberg games and Bayesian Persuasion in Machine Learning - Wednesday, 13.11.2024, 14:30
by Huynh Quang Kiet Vo 11 Nov '24

11 Nov '24

Dear all, For this week's reading group on Wednesday, we will continue our Decision Making series and I will present (1) the Stackelberg games, their connection to Strategic Classification (or Strategic Learning in general), (2) Bayesian Persuasion, and its connection to Algorithmic Recourse. The session will take place at 14:30 (on Wednesday) in CISPA's D2 building, room 1.16 and via the usual Zoom link, which you can find from the google sheet. We look forward to your participation. Best Regards, Kiet Vo

1 0

2025

2024

2023

Ml-reading-group November 2024

2025

2024

2023

Ml-reading-group November 2024 ----- 2025 ----- February 2025 January 2025 ----- 2024 ----- December 2024 November 2024 October 2024 September 2024 August 2024 July 2024 June 2024 May 2024 April 2024 March 2024 February 2024 January 2024 ----- 2023 ----- December 2023 November 2023 October 2023

Ml-reading-group November 2024