Master 2 IASD (ENS Ulm)
Context-dependent collective decisions.
Traditional research in social choice (axiomatic or computational) consists in proposing collective decision mechanisms that are often too rigid. We will focus on the development of families of parameterized rules, which have enough variability and flexibility to allow the development of “tailor-made” mechanisms for specific problems.
PhD in Computer Science at LAMSADE – Paris-Dauphine
How does changing the voting system and the electoral district boundaries impact the outcome of the French legislative elections?
The aim of the project is to study the impact of changing the voting system (mixed electoral system, proportional representation …) and the electoral district boundaries on the outcome of the French legislative elections of 2017.
PhD Student
Université PSL
tahar.allouche [at] dauphine.eu
Mathematical Engineering degree from ENSTA Paris – M2 Optimization from Paris-Saclay university
Learning societal preferences for automated collective decision making.
We study sophisticated models of agents’ preferences as data structure in a learning framework for collective decision aiding. Statistical, computational and epistemic aspects of the preferences are considered in order to thoroughly explore their structure and efficiently infer optimal decisions.
PhD Student
INRIA
alafate.abulimiti [at] inria.fr
Master degree in Big Data Management and Analytic, University of Tours
Engineer degree in Computer Science, Polytech Tours
Bachelor degree in Applied Physics, Beijing Institute of Technology
The role of rapport in human-conversational agent interaction: Modeling conversation to improve task performance in human-agent interaction.
Human interaction is a complex process, and understanding and structuring the dynamics of the conversation is a necessary step to produce a virtual agent capable of interacting as a social agent. The rapport is a very important factor in the design of social agents. The social agent chooses the proper conversational actions according to the verbal and non-verbal characteristics of the interlocutor in order to maintain or increase the level of rapport while performing a specific task. During the doctoral program, I will use the decision system supported by game theory and deep reinforcement learning to build different models. Then, by using different metrics, I will evaluate whether the addition of these models can improve agent performance.
Multi-agent systems, Knowledge representation and reasoning
lang [at] lamsade.dauphine.fr
CNRS senior scientist (2008-), LAMSADE (CNRS, PSL, Université Paris-Dauphine). CNRS silver medal 2017. EurAI fellow since 2009. Associate editor of Journal of Artificial Intelligence Research (2009-2015), Artificial Intelligence Journal (2010-2016), Social Choice and Welfare (2016-). Program chair of IJCAIECAI-2018, General chair of ECAI-2020. Recipient of the Humboldt Research Award 2021.
Computational social choice, algorithmic game theory, fairness, algorithmic decision theory, knowledge representation
Jérôme Lang’s research project focuses on the use of social-choice theoretic, decision-theoretic, and game-theoretic principles and tools for AI. This goes in two opposite directions: from economics to AI, and from AI to economics. He will especially focus in domains where AI helps taking decisions for groups of people. He plans to work on social-choice principles for ethics and fairness in AI, and more generally for assessing the social acceptability of AI algorithms.
Normative criteria developed in economics (such as fairness, equity, anonymity, privacy, strategyproofness, efficiency), can be help defining frameworks for analysing the ethics and social acceptability of AI algorithms, and investigating the trade-offs that have to be made between incompatible criteria. Notions of fairness in AI and social choice are slightly different but convergent, and the various notions of fairness studied in social choice are relevant to AI research. Moreover, AI techniques are useful for making collective decisions: especially, ML methods for learning and eliciting users’ preferences help making collective decisions that offer a good trade-off between the quality of the outcome and the communication burden. This applies to various areas of public decision making, such as allocation problems (matching students to universities, organs to patients, designing fair and robust schedules in hospitals or high schools), or fair and efficient public spending.
Professor, Computer Science, LAMSADE, University Paris-Dauphine, PSL (Sep. 2008-). Editor in Chief: International Computer Games Association Journal (2017-).
Artificial Intelligence, Monte Carlo Search, Deep Learning, Games, Optimization
Tristan Cazenave will address Monte Carlo Search and Deep Reinforcement Learning for games and optimization problems. He will act as the director of the IASD research master in Artificial Intelligence of PSL.
My current research topics are:
• Tailor the Monte Carlo search to the problem being learned. For example for single player games a Nested Monte Carlo search might learn better than the standard PUCT search. Similarly for incomplete information problems PUCT might not be the best algorithm.
• Accelerate Alpha Zero type Deep Reinforcement Learning. The current algorithm requires huge computations. Finding ways to learn faster is important.
• Apply a combination of Monte Carlo search and Deep Learning to various
optimization problems.
• Explore various network architectures. For example residual networks enable to train deeper net-works faster and with better results. Layers such as Average Spatial Pooling improve much the quality of value networks. New network architectures may improve substantially the level of play.
