no code implementations • 25 Jan 2024 • Stephen Casper, Carson Ezell, Charlotte Siegmann, Noam Kolt, Taylor Lynn Curtis, Benjamin Bucknall, Andreas Haupt, Kevin Wei, Jérémy Scheurer, Marius Hobbhahn, Lee Sharkey, Satyapriya Krishna, Marvin Von Hagen, Silas Alberti, Alan Chan, Qinyi Sun, Michael Gerovitch, David Bau, Max Tegmark, David Krueger, Dylan Hadfield-Menell
External audits of AI systems are increasingly recognized as a key mechanism for AI governance.
no code implementations • 13 Feb 2023 • Andreas Haupt, Dylan Hadfield-Menell, Chara Podimata
We model this user behavior as a two-stage noisy signalling game between the recommendation system and users: the recommendation system initially commits to a recommendation policy, presents content to the users during a cold start phase which the users choose to strategically consume in order to affect the types of content they will be recommended in a recommendation phase.
no code implementations • 31 Jan 2023 • Andreas Haupt, Zoe Hitzig
In a described contract, the principal sorts the agents into groups, and to each group communicates a distribution of output-contingent payments.
no code implementations • 1 Aug 2022 • Mihaela Curmei, Andreas Haupt, Dylan Hadfield-Menell, Benjamin Recht
Second, we discuss implications of dynamic preference models for recommendation systems evaluation and design.
no code implementations • 10 May 2022 • Andreas Haupt, Aroon Narayanan
The first method requires the algorithm to reweight data as a function of how likely the actions were to be chosen.
no code implementations • 20 Dec 2021 • Andreas Haupt, Zoë Hitzig
We introduce a framework for comparing the privacy of different mechanisms.
no code implementations • 26 Mar 2021 • Andreas Haupt, Vaikkunth Mugunthan
Federated learning (FL) is a paradigm that allows distributed clients to learn a shared machine learning model without sharing their sensitive training data.
no code implementations • 24 Oct 2017 • Andreas Haupt, Mohammad Khatami, Thomas Schultz, Ngoc Mai Tran
When each data point is a large graph, graph statistics such as densities of certain subgraphs (motifs) can be used as feature vectors for machine learning.