Search Results

Documents authored by Daskalakis, Constantinos

Document
DOI: 10.4230/LIPIcs.ITCS.2024.37
Smooth Nash Equilibria: Algorithms and Complexity

Authors: Constantinos Daskalakis, Noah Golowich, Nika Haghtalab, and Abhishek Shetty

Published in: LIPIcs, Volume 287, 15th Innovations in Theoretical Computer Science Conference (ITCS 2024)

Abstract
A fundamental shortcoming of the concept of Nash equilibrium is its computational intractability: approximating Nash equilibria in normal-form games is PPAD-hard. In this paper, inspired by the ideas of smoothed analysis, we introduce a relaxed variant of Nash equilibrium called σ-smooth Nash equilibrium, for a {smoothness parameter} σ. In a σ-smooth Nash equilibrium, players only need to achieve utility at least as high as their best deviation to a σ-smooth strategy, which is a distribution that does not put too much mass (as parametrized by σ) on any fixed action. We distinguish two variants of σ-smooth Nash equilibria: strong σ-smooth Nash equilibria, in which players are required to play σ-smooth strategies under equilibrium play, and weak σ-smooth Nash equilibria, where there is no such requirement. We show that both weak and strong σ-smooth Nash equilibria have superior computational properties to Nash equilibria: when σ as well as an approximation parameter ϵ and the number of players are all constants, there is a {constant-time} randomized algorithm to find a weak ϵ-approximate σ-smooth Nash equilibrium in normal-form games. In the same parameter regime, there is a polynomial-time deterministic algorithm to find a strong ϵ-approximate σ-smooth Nash equilibrium in a normal-form game. These results stand in contrast to the optimal algorithm for computing ϵ-approximate Nash equilibria, which cannot run in faster than quasipolynomial-time, subject to complexity-theoretic assumptions. We complement our upper bounds by showing that when either σ or ϵ is an inverse polynomial, finding a weak ϵ-approximate σ-smooth Nash equilibria becomes computationally intractable. Our results are the first to propose a variant of Nash equilibrium which is computationally tractable, allows players to act independently, and which, as we discuss, is justified by an extensive line of work on individual choice behavior in the economics literature.
Cite as

Constantinos Daskalakis, Noah Golowich, Nika Haghtalab, and Abhishek Shetty. Smooth Nash Equilibria: Algorithms and Complexity. In 15th Innovations in Theoretical Computer Science Conference (ITCS 2024). Leibniz International Proceedings in Informatics (LIPIcs), Volume 287, pp. 37:1-37:22, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@InProceedings{daskalakis_et_al:LIPIcs.ITCS.2024.37,
  author =	{Daskalakis, Constantinos and Golowich, Noah and Haghtalab, Nika and Shetty, Abhishek},
  title =	{{Smooth Nash Equilibria: Algorithms and Complexity}},
  booktitle =	{15th Innovations in Theoretical Computer Science Conference (ITCS 2024)},
  pages =	{37:1--37:22},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-309-6},
  ISSN =	{1868-8969},
  year =	{2024},
  volume =	{287},
  editor =	{Guruswami, Venkatesan},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ITCS.2024.37},
  URN =		{urn:nbn:de:0030-drops-195657},
  doi =		{10.4230/LIPIcs.ITCS.2024.37},
  annote =	{Keywords: Nash equilibrium, smoothed analysis, PPAD}
}
Document
Invited Talk
DOI: 10.4230/LIPIcs.ICALP.2022.2
Equilibrium Computation, Deep Learning, and Multi-Agent Reinforcement Learning (Invited Talk)

Authors: Constantinos Daskalakis

Published in: LIPIcs, Volume 229, 49th International Colloquium on Automata, Languages, and Programming (ICALP 2022)

Abstract
Machine Learning has recently made significant advances in challenges such as speech and image recognition, automatic translation, and text generation, much of that progress being fueled by the success of gradient descent-based optimization methods in computing local optima of non-convex objectives. From robustifying machine learning models against adversarial attacks to causal inference, training generative models, multi-robot interactions, and learning in strategic environments, many outstanding challenges in Machine Learning lie at its interface with Game Theory. On this front, however, gradient-descent based optimization methods have been less successful. Here, the role of single-objective optimization is played by equilibrium computation, but gradient-descent based methods commonly fail to find equilibria, and even computing local approximate equilibria has remained daunting. We shed light on these challenges through a combination of learning-theoretic, complexity-theoretic, game-theoretic and topological techniques, presenting obstacles and opportunities for Machine Learning and Game Theory going forward. I will assume no Deep Learning background for this talk and present results from joint works with S. Skoulakis and M. Zampetakis [Daskalakis et al., 2021] as well as with N. Golowich and K. Zhang [Daskalakis et al., 2022].
Cite as

Constantinos Daskalakis. Equilibrium Computation, Deep Learning, and Multi-Agent Reinforcement Learning (Invited Talk). In 49th International Colloquium on Automata, Languages, and Programming (ICALP 2022). Leibniz International Proceedings in Informatics (LIPIcs), Volume 229, p. 2:1, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)

Copy BibTex To Clipboard

@InProceedings{daskalakis:LIPIcs.ICALP.2022.2,
  author =	{Daskalakis, Constantinos},
  title =	{{Equilibrium Computation, Deep Learning, and Multi-Agent Reinforcement Learning}},
  booktitle =	{49th International Colloquium on Automata, Languages, and Programming (ICALP 2022)},
  pages =	{2:1--2:1},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-235-8},
  ISSN =	{1868-8969},
  year =	{2022},
  volume =	{229},
  editor =	{Boja\'{n}czyk, Miko{\l}aj and Merelli, Emanuela and Woodruff, David P.},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ICALP.2022.2},
  URN =		{urn:nbn:de:0030-drops-163431},
  doi =		{10.4230/LIPIcs.ICALP.2022.2},
  annote =	{Keywords: Deep Learning, Multi-Agent (Reinforcement) Learning, Game Theory, Nonconvex Optimization, PPAD}
}
Document
DOI: 10.4230/LIPIcs.ITCS.2019.27
Last-Iterate Convergence: Zero-Sum Games and Constrained Min-Max Optimization

Authors: Constantinos Daskalakis and Ioannis Panageas

Published in: LIPIcs, Volume 124, 10th Innovations in Theoretical Computer Science Conference (ITCS 2019)

Abstract
Motivated by applications in Game Theory, Optimization, and Generative Adversarial Networks, recent work of Daskalakis et al [Daskalakis et al., ICLR, 2018] and follow-up work of Liang and Stokes [Liang and Stokes, 2018] have established that a variant of the widely used Gradient Descent/Ascent procedure, called "Optimistic Gradient Descent/Ascent (OGDA)", exhibits last-iterate convergence to saddle points in unconstrained convex-concave min-max optimization problems. We show that the same holds true in the more general problem of constrained min-max optimization under a variant of the no-regret Multiplicative-Weights-Update method called "Optimistic Multiplicative-Weights Update (OMWU)". This answers an open question of Syrgkanis et al [Syrgkanis et al., NIPS, 2015]. The proof of our result requires fundamentally different techniques from those that exist in no-regret learning literature and the aforementioned papers. We show that OMWU monotonically improves the Kullback-Leibler divergence of the current iterate to the (appropriately normalized) min-max solution until it enters a neighborhood of the solution. Inside that neighborhood we show that OMWU becomes a contracting map converging to the exact solution. We believe that our techniques will be useful in the analysis of the last iterate of other learning algorithms.
Cite as

Constantinos Daskalakis and Ioannis Panageas. Last-Iterate Convergence: Zero-Sum Games and Constrained Min-Max Optimization. In 10th Innovations in Theoretical Computer Science Conference (ITCS 2019). Leibniz International Proceedings in Informatics (LIPIcs), Volume 124, pp. 27:1-27:18, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2019)

Copy BibTex To Clipboard

@InProceedings{daskalakis_et_al:LIPIcs.ITCS.2019.27,
  author =	{Daskalakis, Constantinos and Panageas, Ioannis},
  title =	{{Last-Iterate Convergence: Zero-Sum Games and Constrained Min-Max Optimization}},
  booktitle =	{10th Innovations in Theoretical Computer Science Conference (ITCS 2019)},
  pages =	{27:1--27:18},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-095-8},
  ISSN =	{1868-8969},
  year =	{2019},
  volume =	{124},
  editor =	{Blum, Avrim},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ITCS.2019.27},
  URN =		{urn:nbn:de:0030-drops-101204},
  doi =		{10.4230/LIPIcs.ITCS.2019.27},
  annote =	{Keywords: No regret learning, Zero-sum games, Convergence, Dynamical Systems, KL divergence}
}
Document
DOI: 10.4230/LIPIcs.ESA.2017.32
Optimal Stopping Rules for Sequential Hypothesis Testing

Authors: Constantinos Daskalakis and Yasushi Kawase

Published in: LIPIcs, Volume 87, 25th Annual European Symposium on Algorithms (ESA 2017)

Abstract
Suppose that we are given sample access to an unknown distribution p over n elements and an explicit distribution q over the same n elements. We would like to reject the null hypothesis "p=q" after seeing as few samples as possible, when p =/= q, while we never want to reject the null, when p=q. Well-known results show that Theta(sqrt{n}/epsilon^2) samples are necessary and sufficient for distinguishing whether p equals q versus p is epsilon-far from q in total variation distance. However, this requires the distinguishing radius epsilon to be fixed prior to deciding how many samples to request. Our goal is instead to design sequential hypothesis testers, i.e. online algorithms that request i.i.d. samples from p and stop as soon as they can confidently reject the hypothesis p=q, without being given a lower bound on the distance between p and q, when p =/= q. In particular, we want to minimize the number of samples requested by our tests as a function of the distance between p and q, and if p=q we want the algorithm, with high probability, to never reject the null. Our work is motivated by and addresses the practical challenge of sequential A/B testing in Statistics. We show that, when n=2, any sequential hypothesis test must see Omega(1/{d_{tv}(p,q)^2} log log 1/{d_{tv}(p,q)}) samples, with high (constant) probability, before it rejects p=q, where d_{tv}(p,q) is the - unknown to the tester - total variation distance between p and q. We match the dependence of this lower bound on d_{tv}(p,q) by proposing a sequential tester that rejects p=q from at most O({\sqrt{n}}/{d_{tv}(p,q)^2}log log 1/{d_{tv}(p,q)}) samples with high (constant) probability. The Omega(sqrt{n}) dependence on the support size n is also known to be necessary. We similarly provide two-sample sequential hypothesis testers, when sample access is given to both p and q, and discuss applications to sequential A/B testing.
Cite as

Constantinos Daskalakis and Yasushi Kawase. Optimal Stopping Rules for Sequential Hypothesis Testing. In 25th Annual European Symposium on Algorithms (ESA 2017). Leibniz International Proceedings in Informatics (LIPIcs), Volume 87, pp. 32:1-32:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2017)

Copy BibTex To Clipboard

@InProceedings{daskalakis_et_al:LIPIcs.ESA.2017.32,
  author =	{Daskalakis, Constantinos and Kawase, Yasushi},
  title =	{{Optimal Stopping Rules for Sequential Hypothesis Testing}},
  booktitle =	{25th Annual European Symposium on Algorithms (ESA 2017)},
  pages =	{32:1--32:14},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-049-1},
  ISSN =	{1868-8969},
  year =	{2017},
  volume =	{87},
  editor =	{Pruhs, Kirk and Sohler, Christian},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ESA.2017.32},
  URN =		{urn:nbn:de:0030-drops-78237},
  doi =		{10.4230/LIPIcs.ESA.2017.32},
  annote =	{Keywords: property testing, sequential hypothesis testing, A/B testing}
}
Document
DOI: 10.4230/LIPIcs.ICALP.2016.24
The Complexity of Hex and the Jordan Curve Theorem

Authors: Aviv Adler, Constantinos Daskalakis, and Erik D. Demaine

Published in: LIPIcs, Volume 55, 43rd International Colloquium on Automata, Languages, and Programming (ICALP 2016)

Abstract
The Jordan curve theorem and Brouwer's fixed-point theorem are fundamental problems in topology. We study their computational relationship, showing that a stylized computational version of Jordan’s theorem is PPAD-complete, and therefore in a sense computationally equivalent to Brouwer’s theorem. As a corollary, our computational result implies that these two theorems directly imply each other mathematically, complementing Maehara's proof that Brouwer implies Jordan [Maehara, 1984]. We then turn to the combinatorial game of Hex which is related to Jordan's theorem, and where the existence of a winner can be used to show Brouwer's theorem [Gale,1979]. We establish that determining who won an (implicitly encoded) play of Hex is PSPACE-complete by adapting a reduction (due to Goldberg [Goldberg,2015]) from Quantified Boolean Formula (QBF). As this problem is analogous to evaluating the output of a canonical path-following algorithm for finding a Brouwer fixed point - and which is known to be PSPACE-complete [Goldberg/Papadimitriou/Savani, 2013] - we thereby establish a connection between Brouwer, Jordan and Hex higher in the complexity hierarchy.
Cite as

Aviv Adler, Constantinos Daskalakis, and Erik D. Demaine. The Complexity of Hex and the Jordan Curve Theorem. In 43rd International Colloquium on Automata, Languages, and Programming (ICALP 2016). Leibniz International Proceedings in Informatics (LIPIcs), Volume 55, pp. 24:1-24:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2016)

Copy BibTex To Clipboard

@InProceedings{adler_et_al:LIPIcs.ICALP.2016.24,
  author =	{Adler, Aviv and Daskalakis, Constantinos and Demaine, Erik D.},
  title =	{{The Complexity of Hex and the Jordan Curve Theorem}},
  booktitle =	{43rd International Colloquium on Automata, Languages, and Programming (ICALP 2016)},
  pages =	{24:1--24:14},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-013-2},
  ISSN =	{1868-8969},
  year =	{2016},
  volume =	{55},
  editor =	{Chatzigiannakis, Ioannis and Mitzenmacher, Michael and Rabani, Yuval and Sangiorgi, Davide},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ICALP.2016.24},
  URN =		{urn:nbn:de:0030-drops-63032},
  doi =		{10.4230/LIPIcs.ICALP.2016.24},
  annote =	{Keywords: Jordan, Brouwer, Hex, PPAD, PSPACE}
}
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail
© 2023-2024 Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact