You need to log in to edit.

You can create a new account if you don't have one.

Or, discuss a change on Slack.

You can create a new account if you don't have one.

Or, discuss a change on Slack.

no code implementations • ICML 2020 • Sai Ganesh Nagarajan, David Balduzzi, Georgios Piliouras

Even simple games learning dynamics can yield chaotic behavior.

1 code implementation • 23 Nov 2023 • Jonah Brown-Cohen, Geoffrey Irving, Georgios Piliouras

The emergence of pre-trained AI systems with powerful capabilities across a diverse and ever-increasing set of complex domains has raised a critical challenge for AI safety as tasks can become too complicated for humans to judge directly.

no code implementations • 17 Nov 2023 • Francisca Vasconcelos, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Panayotis Mertikopoulos, Georgios Piliouras, Michael I. Jordan

In 2008, Jain and Watrous proposed the first classical algorithm for computing equilibria in quantum zero-sum games using the Matrix Multiplicative Weight Updates (MMWU) method to achieve a convergence rate of $\mathcal{O}(d/\epsilon^2)$ iterations to $\epsilon$-Nash equilibria in the $4^d$-dimensional spectraplex.

no code implementations • 26 Jul 2023 • Aamal Hussain, Dan Leonte, Francesco Belardinelli, Georgios Piliouras

The behaviour of multi-agent learning in many player games has been shown to display complex dynamics outside of restrictive examples such as network zero-sum games.

no code implementations • 13 Jul 2023 • Iosif Sakos, Antonios Varvitsiotis, Georgios Piliouras

In this work, we propose a theoretical and algorithmic framework for real-time identification of the learning dynamics that govern agent behavior using a short burst of a single system trajectory.

no code implementations • 6 Jul 2023 • Ilayda Canyakmaz, Wayne Lin, Georgios Piliouras, Antonios Varvitsiotis

We study online convex optimization where the possible actions are trace-one elements in a symmetric cone, generalizing the extensively-studied experts setup and its quantum counterpart.

no code implementations • 1 Jun 2023 • Emmanouil-Vasileios Vlatakis-Gkaragkounis, Lampros Flokas, Georgios Piliouras

Although such techniques are known to allow for improved convergence guarantees in small games, it has been much harder to analyze them in more relevant settings with large populations of agents.

no code implementations • 23 Jan 2023 • Aamal Abbas Hussain, Francesco Belardinelli, Georgios Piliouras

Achieving convergence of multiple learning agents in general $N$-player games is imperative for the development of safe and reliable machine learning (ML) algorithms and their application to autonomous systems.

no code implementations • 10 Jan 2023 • Volkan Cevher, Georgios Piliouras, Ryann Sim, Stratis Skoulakis

In this paper we present a first-order method that admits near-optimal convergence rates for convex/concave min-max problems while requiring a simple and intuitive analysis.

no code implementations • 22 Aug 2022 • Paul Muller, Romuald Elie, Mark Rowland, Mathieu Lauriere, Julien Perolat, Sarah Perrin, Matthieu Geist, Georgios Piliouras, Olivier Pietquin, Karl Tuyls

The designs of many large-scale systems today, from traffic routing environments to smart grids, rely on game-theoretic equilibrium concepts.

no code implementations • 18 Jul 2022 • Georgios Piliouras, Lillian Ratliff, Ryann Sim, Stratis Skoulakis

The study of learning in games has thus far focused primarily on normal form games.

no code implementations • 8 Jun 2022 • Andre Wibisono, Molei Tao, Georgios Piliouras

In this paper we study two-player bilinear zero-sum games with constrained strategy spaces.

no code implementations • 26 Mar 2022 • Jason Milionis, Christos Papadimitriou, Georgios Piliouras, Kelly Spendlove

We also prove a stronger result for $\epsilon$-approximate Nash equilibria: there are games such that no game dynamics can converge (in an appropriate sense) to $\epsilon$-Nash equilibria, and in fact the set of such games has positive measure.

no code implementations • 22 Mar 2022 • Mathieu Laurière, Sarah Perrin, Sertan Girgin, Paul Muller, Ayush Jain, Theophile Cabannes, Georgios Piliouras, Julien Pérolat, Romuald Élie, Olivier Pietquin, Matthieu Geist

One limiting factor to further scale up using RL is that existing algorithms to solve MFGs require the mixing of approximated quantities such as strategies or $q$-values.

no code implementations • 24 Feb 2022 • Gabriel P. Andrade, Rafael Frongillo, Georgios Piliouras

Games are natural models for multi-agent machine learning settings, such as generative adversarial networks (GANs).

no code implementations • 25 Jan 2022 • Georgios Piliouras, Fang-Yi Yu

The recent framework of performative prediction is aimed at capturing settings where predictions influence the target/outcome they want to predict.

no code implementations • 29 Nov 2021 • Georgios Piliouras, Ryann Sim, Stratis Skoulakis

This implies that the CMWU dynamics converge with rate $O(nV \log m \log T / T)$ to a \textit{Coarse Correlated Equilibrium}.

no code implementations • NeurIPS 2021 • Tanner Fiez, Ryann Sim, Stratis Skoulakis, Georgios Piliouras, Lillian Ratliff

Classical learning results build on this theorem to show that online no-regret dynamics converge to an equilibrium in a time-average sense in zero-sum games.

no code implementations • ICLR 2022 • Andjela Mladenovic, Iosif Sakos, Gauthier Gidel, Georgios Piliouras

In the case of Fisher information geometry, we provide a complete picture of the dynamics in an interesting special setting of team competition via invariant function analysis.

no code implementations • ICLR 2022 • Yun Kuen Cheung, Georgios Piliouras, Yixin Tao

We study standard online learning in games but from a non-standard perspective.

no code implementations • 8 Sep 2021 • Georgios Piliouras, Xiao Wang

Several recent works in online optimization and game dynamics have established strong negative complexity results including the formal emergence of instability and chaos even in small such settings, e. g., $2\times 2$ games.

no code implementations • 28 Jun 2021 • Georgios Piliouras, Mark Rowland, Shayegan Omidshafiei, Romuald Elie, Daniel Hennes, Jerome Connor, Karl Tuyls

Importantly, $\Phi$-regret enables learning agents to consider deviations from and to mixed strategies, generalizing several existing notions of regret such as external, internal, and swap regret, and thus broadening the insights gained from regret-based analysis of learning algorithms.

no code implementations • NeurIPS 2021 • Stefanos Leonardos, Georgios Piliouras, Kelly Spendlove

The interplay between exploration and exploitation in competitive multi-agent learning is still far from being well understood.

no code implementations • 9 Jun 2021 • Yun Kuen Cheung, Georgios Piliouras

Passivity is a fundamental concept in control theory, which abstracts energy conservation and dissipation in physical systems.

no code implementations • 8 Jun 2021 • Dimitris Fotakis, Georgios Piliouras, Stratis Skoulakis

We study dynamic clustering problems from the perspective of online learning.

1 code implementation • NeurIPS 2021 • Stefanos Leonardos, Will Overman, Ioannis Panageas, Georgios Piliouras

Counter-intuitively, insights from normal-form potential games do not carry over as MPGs can consist of settings where state-games can be zero-sum games.

no code implementations • 5 Mar 2021 • Gabriel P. Andrade, Rafael Frongillo, Georgios Piliouras

In this paper we show that, in a strong sense, this dynamic complexity is inherent to games.

1 code implementation • 28 Feb 2021 • Julien Perolat, Sarah Perrin, Romuald Elie, Mathieu Laurière, Georgios Piliouras, Matthieu Geist, Karl Tuyls, Olivier Pietquin

We address scaling up equilibrium computation in Mean Field Games (MFGs) using Online Mirror Descent (OMD).

no code implementations • 16 Feb 2021 • Jakub Bielawski, Thiparat Chotibut, Fryderyk Falniowski, Grzegorz Kosiorowski, Michał Misiurewicz, Georgios Piliouras

We establish that, even in simple linear non-atomic congestion games with two parallel links and any fixed learning rate, unless the game is fully symmetric, increasing the population size or the scale of costs causes learning dynamics to become unstable and eventually chaotic, in the sense of Li-Yorke and positive topological entropy.

no code implementations • NeurIPS 2021 • Lampros Flokas, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Georgios Piliouras

Inspired by this, we study standard gradient descent ascent (GDA) dynamics in a specific class of non-convex non-concave zero-sum games, that we call hidden zero-sum games.

1 code implementation • 15 Dec 2020 • Stratis Skoulakis, Tanner Fiez, Ryann Sim, Georgios Piliouras, Lillian Ratliff

The predominant paradigm in evolutionary game theory and more generally online learning in games is based on a clear distinction between a population of dynamic agents that interact given a fixed, static game.

no code implementations • 5 Dec 2020 • Stefanos Leonardos, Georgios Piliouras

Exploration-exploitation is a powerful and practical tool in multi-agent learning (MAL), however, its effects are far from understood.

Q-Learning Computer Science and Game Theory Multiagent Systems Dynamical Systems 93A16, 91A26, 91A68, 58K35 G.3; J.4; F.2.2

1 code implementation • NeurIPS 2020 • Dimitris Fotakis, Thanasis Lianeas, Georgios Piliouras, Stratis Skoulakis

We consider a natural model of online preference aggregation, where sets of preferred items $R_1, R_2, \ldots, R_t$ along with a demand for $k_t$ items in each $R_t$, appear online.

no code implementations • NeurIPS 2020 • Lampros Flokas, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Thanasis Lianeas, Panayotis Mertikopoulos, Georgios Piliouras

Understanding the behavior of no-regret dynamics in general $N$-player games is a fundamental question in online learning and game theory.

no code implementations • NeurIPS 2020 • Yun Kuen Cheung, Georgios Piliouras

We present volume analyses of Multiplicative Weights Updates (MWU) and Optimistic Multiplicative Weights Updates (OMWU) in zero-sum as well as coordination games.

no code implementations • 19 Feb 2020 • Julien Perolat, Remi Munos, Jean-Baptiste Lespiau, Shayegan Omidshafiei, Mark Rowland, Pedro Ortega, Neil Burch, Thomas Anthony, David Balduzzi, Bart De Vylder, Georgios Piliouras, Marc Lanctot, Karl Tuyls

In this paper we investigate the Follow the Regularized Leader dynamics in sequential imperfect information games (IIG).

no code implementations • ICLR 2020 • David Balduzzi, Wojciech M. Czarnecki, Thomas W. Anthony, Ian M Gemp, Edward Hughes, Joel Z. Leibo, Georgios Piliouras, Thore Graepel

With the success of modern machine learning, it is becoming increasingly important to understand and control how learning algorithms interact.

1 code implementation • NeurIPS 2019 • Lampros Flokas, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Georgios Piliouras

We consider the case of derivative-free algorithms for non-convex optimization, also known as zero order algorithms, that use only function evaluations rather than gradients.

1 code implementation • NeurIPS 2019 • Lampros Flokas, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Georgios Piliouras

We study a wide class of non-convex non-concave min-max games that generalizes over standard bilinear zero-sum games.

no code implementations • 24 Sep 2019 • Constandina Koki, Stefanos Leonardos, Georgios Piliouras

Conventional financial models fail to explain the economic and monetary properties of cryptocurrencies due to the latter's dual nature: their usage as financial assets on the one side and their tight connection to the underlying blockchain structure on the other.

1 code implementation • NeurIPS 2019 • Mark Rowland, Shayegan Omidshafiei, Karl Tuyls, Julien Perolat, Michal Valko, Georgios Piliouras, Remi Munos

This paper investigates the evaluation of learned multiagent strategies in the incomplete information setting, which plays a critical role in ranking and training of agents.

no code implementations • 9 Jul 2019 • James P. Bailey, Gauthier Gidel, Georgios Piliouras

Gradient descent is arguably one of the most popular online optimization methods with a wide array of applications.

Computer Science and Game Theory Dynamical Systems Optimization and Control

no code implementations • NeurIPS 2019 • James P. Bailey, Georgios Piliouras

We show for the first time, to our knowledge, that it is possible to reconcile in online learning in zero-sum games two seemingly contradictory objectives: vanishing time-average regret and non-vanishing step sizes.

no code implementations • ICLR 2019 • Panayotis Mertikopoulos, Bruno Lecouat, Houssam Zenati, Chuan-Sheng Foo, Vijay Chandrasekhar, Georgios Piliouras

Owing to their connection with generative adversarial networks (GANs), saddle-point problems have recently attracted considerable interest in machine learning and beyond.

no code implementations • 5 Mar 2019 • James P. Bailey, Georgios Piliouras

Specifically, we show that no matter the size, or network structure of such closed economies, even if agents use different online learning dynamics from the standard class of Follow-the-Regularized-Leader, they yield Hamiltonian dynamics.

1 code implementation • 4 Mar 2019 • Shayegan Omidshafiei, Christos Papadimitriou, Georgios Piliouras, Karl Tuyls, Mark Rowland, Jean-Baptiste Lespiau, Wojciech M. Czarnecki, Marc Lanctot, Julien Perolat, Remi Munos

We introduce {\alpha}-Rank, a principled evolutionary dynamics methodology, for the evaluation and ranking of agents in large-scale multi-agent interactions, grounded in a novel dynamical game-theoretic solution concept called Markov-Conley chains (MCCs).

1 code implementation • 16 Feb 2019 • Francisco Benita, Garvit Bansal, Georgios Piliouras, Bige Tunçer

This study models and examines commuter's preferences for short-distance transportation modes, namely: walking, taking a bus or riding a metro.

1 code implementation • 9 Feb 2019 • Yasin Yazici, Bruno Lecouat, Chuan-Sheng Foo, Stefan Winkler, Kim-Hui Yap, Georgios Piliouras, Vijay Chandrasekhar

We propose a GAN design which models multiple distributions effectively and discovers their commonalities and particularities.

no code implementations • 7 Jul 2018 • Panayotis Mertikopoulos, Bruno Lecouat, Houssam Zenati, Chuan-Sheng Foo, Vijay Chandrasekhar, Georgios Piliouras

Owing to their connection with generative adversarial networks (GANs), saddle-point problems have recently attracted considerable interest in machine learning and beyond.

1 code implementation • ICLR 2019 • Yasin Yazici, Chuan-Sheng Foo, Stefan Winkler, Kim-Hui Yap, Georgios Piliouras, Vijay Chandrasekhar

We examine two different techniques for parameter averaging in GAN training.

no code implementations • NeurIPS 2017 • Gerasimos Palaiopanos, Ioannis Panageas, Georgios Piliouras

Interestingly, this convergence result does not carry over to the nearly homologous MWU variant where at each step the probability assigned to action $\gamma$ is multiplied by $(1 -\epsilon)^{C(\gamma)}$ even for the simplest case of two-agent, two-strategy load balancing games, where such dynamics can provably lead to limit cycles or even chaotic behavior.

no code implementations • 20 Oct 2017 • Jason D. Lee, Ioannis Panageas, Georgios Piliouras, Max Simchowitz, Michael. I. Jordan, Benjamin Recht

We establish that first-order methods avoid saddle points for almost all initializations.

no code implementations • 8 Sep 2017 • Panayotis Mertikopoulos, Christos Papadimitriou, Georgios Piliouras

Regularized learning is a fundamental technique in online optimization, machine learning and many other fields of computer science.

1 code implementation • 17 Jun 2017 • Zhe Wang, Kingsley Kuan, Mathieu Ravaut, Gaurav Manek, Sibo Song, Yuan Fang, Seokhwan Kim, Nancy Chen, Luis Fernando D'Haro, Luu Anh Tuan, Hongyuan Zhu, Zeng Zeng, Ngai Man Cheung, Georgios Piliouras, Jie Lin, Vijay Chandrasekhar

Beyond that, we extend the original competition by including text information in the classification, making this a truly multi-modal approach with vision, audio and text.

no code implementations • 25 Apr 2017 • Tushar Vaidya, Carlos Murguia, Georgios Piliouras

Black-Scholes (BS) is the standard mathematical model for option pricing in financial markets.

no code implementations • 2 May 2016 • Ioannis Panageas, Georgios Piliouras

Given a non-convex twice differentiable cost function f, we prove that the set of initial conditions so that gradient descent converges to saddle points where \nabla^2 f has at least one strictly negative eigenvalue has (Lebesgue) measure zero, even for cost functions f with non-isolated critical points, answering an open question in [Lee, Simchowitz, Jordan, Recht, COLT2016].

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

Contact us on:
hello@paperswithcode.com
.
Papers With Code is a free resource with all data licensed under CC-BY-SA.