Search Results for author: Vincent Conitzer

Found 37 papers, 7 papers with code

Learning the Valuations of a $k$-demand Agent

no code implementations ICML 2020 Hanrui Zhang, Vincent Conitzer

We study problems where a learner aims to learn the valuations of an agent by observing which goods he buys under varying price vectors.

Active Learning

Learning and Computation of $Φ$-Equilibria at the Frontier of Tractability

no code implementations25 Feb 2025 Brian Hu Zhang, Ioannis Anagnostides, Emanuel Tewolde, Ratip Emin Berker, Gabriele Farina, Vincent Conitzer, Tuomas Sandholm

At the heart of our approach is a polynomial-time algorithm for computing an expected fixed point of any $\phi : \mathcal{X} \to \mathcal{X}$ based on the ellipsoid against hope (EAH) algorithm of Papadimitriou and Roughgarden (JACM '08).

Expected Variational Inequalities

no code implementations25 Feb 2025 Brian Hu Zhang, Ioannis Anagnostides, Emanuel Tewolde, Ratip Emin Berker, Gabriele Farina, Vincent Conitzer, Tuomas Sandholm

Variational inequalities (VIs) encompass many fundamental problems in diverse areas ranging from engineering to economics and machine learning.

An Interpretable Automated Mechanism Design Framework with Large Language Models

no code implementations16 Feb 2025 Jiayuan Liu, Mingyu Guo, Vincent Conitzer

The code generation capabilities of LLMs enable the discovery of novel and interpretable solutions, bridging the symbolic logic of mechanism design and the generative power of modern AI.

Code Generation

Computing Game Symmetries and Equilibria That Respect Them

no code implementations15 Jan 2025 Emanuel Tewolde, Brian Hu Zhang, Caspar Oesterheld, Tuomas Sandholm, Vincent Conitzer

Strategic interactions can be represented more concisely, and analyzed and solved more efficiently, if we are aware of the symmetries within the multiagent system.

Observation Interference in Partially Observable Assistance Games

no code implementations23 Dec 2024 Scott Emmons, Caspar Oesterheld, Vincent Conitzer, Stuart Russell

We show that this incentive for interference goes away if the human is playing optimally, or if we introduce a communication channel for the human to communicate their preferences to the assistant.

Efficiently Solving Turn-Taking Stochastic Games with Extensive-Form Correlation

no code implementations22 Dec 2024 Hanrui Zhang, Yu Cheng, Vincent Conitzer

Our algorithm for SEFCE is the first polynomial-time algorithm for equilibrium computation with commitment in such a general class of stochastic games.

Form

Characterising Simulation-Based Program Equilibria

no code implementations19 Dec 2024 Emery Cooper, Caspar Oesterheld, Vincent Conitzer

Finally, we explore the limits of simulation-based program equilibrium, showing that the Tennenholtz folk theorem cannot be attained by simulation-based programs without access to shared randomness.

Can CDT rationalise the ex ante optimal policy via modified anthropics?

no code implementations7 Nov 2024 Emery Cooper, Caspar Oesterheld, Vincent Conitzer

If so, then causal decision theory might recommend one-boxing in order to cause the predictor to fill the opaque box.

Game Theory with Simulation in the Presence of Unpredictable Randomisation

no code implementations18 Oct 2024 Vojtech Kovarik, Nathaniel Sauerberg, Lewis Hammond, Vincent Conitzer

As positive results, we establish that mixed-strategy simulation can improve social welfare if the simulator has the option to scale their level of trust, if the players face challenges with both trust and coordination, or if maintaining some level of privacy is essential for enabling cooperation.

On The Stability of Moral Preferences: A Problem with Computational Elicitation Methods

no code implementations5 Aug 2024 Kyle Boerstler, Vijay Keswani, Lok Chan, Jana Schaich Borg, Vincent Conitzer, Hoda Heidari, Walter Sinnott-Armstrong

If participants' moral responses are unstable in such ways, it would raise important methodological and theoretical issues for how participants' true moral preferences, opinions, and judgments can be ascertained.

On the Pros and Cons of Active Learning for Moral Preference Elicitation

no code implementations26 Jul 2024 Vijay Keswani, Vincent Conitzer, Hoda Heidari, Jana Schaich Borg, Walter Sinnott-Armstrong

In this work, we argue that the use of active learning for moral preference elicitation relies on certain assumptions about the underlying moral preferences, which can be violated in practice.

Active Learning

Why should we ever automate moral decision making?

no code implementations10 Jul 2024 Vincent Conitzer

Given this, why should we ever automate moral decision making -- is it not better to leave all moral decision making to humans?

Decision Making Ethics +1

Imperfect-Recall Games: Equilibrium Concepts and Their Complexity

no code implementations23 Jun 2024 Emanuel Tewolde, Brian Hu Zhang, Caspar Oesterheld, Manolis Zampetakis, Tuomas Sandholm, Paul W. Goldberg, Vincent Conitzer

We investigate optimal decision making under imperfect recall, that is, when an agent forgets information it once held before.

Decision Making

Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback

no code implementations16 Apr 2024 Vincent Conitzer, Rachel Freedman, Jobst Heitzig, Wesley H. Holliday, Bob M. Jacobs, Nathan Lambert, Milan Mossé, Eric Pacuit, Stuart Russell, Hailey Schoelkopf, Emanuel Tewolde, William S. Zwicker

Foundation models such as GPT-4 are fine-tuned to avoid unsafe or otherwise problematic behavior, such as helping to commit crimes or producing racist text.

Ethics

Recursive Joint Simulation in Games

no code implementations12 Feb 2024 Vojtech Kovarik, Caspar Oesterheld, Vincent Conitzer

In this paper, we study an interaction between AI agents where the agents run a recursive joint simulation.

AI Agent

A Theory of Bounded Inductive Rationality

no code implementations11 Jul 2023 Caspar Oesterheld, Abram Demski, Vincent Conitzer

In this paper, we develop a theory of rational decision making that does not assume logical omniscience.

Decision Making

The Computational Complexity of Single-Player Imperfect-Recall Games

no code implementations28 May 2023 Emanuel Tewolde, Caspar Oesterheld, Vincent Conitzer, Paul W. Goldberg

For such games, two natural equilibrium concepts have been proposed as alternative solution concepts to ex-ante optimality.

Tradeoffs in Preventing Manipulation in Paper Bidding for Reviewer Assignment

no code implementations22 Jul 2022 Steven Jecmen, Nihar B. Shah, Fei Fang, Vincent Conitzer

Many conferences rely on paper bidding as a key component of their reviewer assignment procedure.

For Learning in Symmetric Teams, Local Optima are Global Nash Equilibria

1 code implementation7 Jul 2022 Scott Emmons, Caspar Oesterheld, Andrew Critch, Vincent Conitzer, Stuart Russell

In this work, we show that any locally optimal symmetric strategy profile is also a (global) Nash equilibrium.

A Dataset on Malicious Paper Bidding in Peer Review

1 code implementation24 Jun 2022 Steven Jecmen, Minji Yoon, Vincent Conitzer, Nihar B. Shah, Fei Fang

The performance of these detection algorithms can be taken as a baseline for future research on detecting malicious bidding.

Descriptive

Efficient Algorithms for Planning with Participation Constraints

no code implementations16 May 2022 Hanrui Zhang, Yu Cheng, Vincent Conitzer

Our approach can also be extended to the (discounted) infinite-horizon case, for which we give an algorithm that runs in time polynomial in the size of the input and $\log(1/\varepsilon)$, and returns a policy that is optimal up to an additive error of $\varepsilon$.

Near-Optimal Reviewer Splitting in Two-Phase Paper Reviewing and Conference Experiment Design

1 code implementation13 Aug 2021 Steven Jecmen, Hanrui Zhang, Ryan Liu, Fei Fang, Vincent Conitzer, Nihar B. Shah

Many scientific conferences employ a two-phase paper review process, where some papers are assigned additional reviewers after the initial reviews are submitted.

Incentive-aware PAC learning

no code implementations Proceedings of the AAAI Conference on Artificial Intelligence 2021 Hanrui Zhang, Vincent Conitzer

We give a sample complexity bound that is, curiously, independent of the hypothesis class, for the ERM principle restricted to incentivecompatible classifiers.

PAC learning

Automated Mechanism Design for Classification with Partial Verification

no code implementations12 Apr 2021 Hanrui Zhang, Yu Cheng, Vincent Conitzer

We study the problem of automated mechanism design with partial verification, where each type can (mis)report only a restricted set of types (rather than any other type), induced by the principal's limited verification power.

Classification General Classification

Classification with Strategically Withheld Data

1 code implementation18 Dec 2020 Anilesh K. Krishnaswamy, Haoming Li, David Rein, Hanrui Zhang, Vincent Conitzer

To this end, we present {\sc IC-LR}, a modification of Logistic Regression that removes the incentive to strategically drop features.

Classification General Classification +1

Indecision Modeling

1 code implementation15 Dec 2020 Duncan C McElfresh, Lok Chan, Kenzie Doyle, Walter Sinnott-Armstrong, Vincent Conitzer, Jana Schaich Borg, John P Dickerson

The philosophy and psychology literature shows that indecision is a measurable and nuanced behavior -- and that there are several different reasons people are indecisive.

Philosophy

Mitigating Manipulation in Peer Review via Randomized Reviewer Assignments

2 code implementations NeurIPS 2020 Steven Jecmen, Hanrui Zhang, Ryan Liu, Nihar B. Shah, Vincent Conitzer, Fei Fang

We further consider the problem of restricting the joint probability that certain suspect pairs of reviewers are assigned to certain papers, and show that this problem is NP-hard for arbitrary constraints on these joint probabilities but efficiently solvable for a practical special case.

Adapting a Kidney Exchange Algorithm to Align with Human Values

1 code implementation19 May 2020 Rachel Freedman, Jana Schaich Borg, Walter Sinnott-Armstrong, John P. Dickerson, Vincent Conitzer

In kidney exchanges, a central market maker allocates living kidney donors to patients in need of an organ.

Distinguishing Distributions When Samples Are Strategically Transformed

no code implementations NeurIPS 2019 Hanrui Zhang, Yu Cheng, Vincent Conitzer

In other settings, the principal may not even be able to observe samples directly; instead, she must rely on signals that the agent is able to send based on the samples that he obtains, and he will choose these signals strategically.

Complexity of Scheduling Charging in the Smart Grid

no code implementations21 Sep 2017 Mathijs de Weerdt, Michael Albert, Vincent Conitzer

In the smart grid, the intent is to use flexibility in demand, both to balance demand and supply as well as to resolve potential congestion.

Scheduling

Multiplicative Pacing Equilibria in Auction Markets

no code implementations22 Jun 2017 Vincent Conitzer, Christian Kroer, Eric Sodomka, Nicolas E. Stier-Moses

Although we show that computing either a social-welfare-maximizing or a revenue-maximizing pacing equilibrium is NP-hard, we present a mixed-integer program (MIP) that can be used to find equilibria optimizing several relevant objectives.

Computer Science and Game Theory

Philosophy in the Face of Artificial Intelligence

no code implementations19 May 2016 Vincent Conitzer

In this article, I discuss how the AI community views concerns about the emergence of superintelligent AI and related philosophical issues.

Philosophy

Cannot find the paper you are looking for? You can Submit a new open access paper.