A game–theoretic approach for Generative Adversarial Networks

Franci, Barbara; Grammatico, Sergio

doi:10.1109/cdc42340.2020.9304183

Cited by 8 publications

(12 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these properties are not necessarily enough to ensure convergence, hence, (quasi) Féjer monotonicity is often used in combination with convergence results on sequences of real numbers. These technical results have been used in many theoretical and computational applications that range from stochastic Nash equilibrium seeking [11,12,14] to machine learning [17,19,20].…”

Section: Lyapunov Decrease and Féjer Monotonicitymentioning

confidence: 99%

“…Since variational inequalities are the mathematical foundations of optimizationrelated problems, such as Nash equilibrium seeking [13,11,21], convex optimization [13,104,23] and machine learning [105,17], many works in the literature rely on the results presented in the previous sections to prove convergence of a given algorithm to a solution of a variational equilibrium problem. Specifically, they are applied to prove that a given algorithm converges to the solution of a variational inequality or to a zero of the sum of (monotone) operators.…”

Section: Applications Of Convergent Deterministic Sequencesmentioning

confidence: 99%

“…Concerning Nash equilibrium problems, it is used in [11,12,111]. In the specific case of generative adversarial networks, Lemma 4.1 is used in [17,18].…”

Section: Other Applicationsmentioning

confidence: 99%

“…The aim of this paper is to collect these results towards a complete overview, thus to be able to find the one that most suits the application at hand. In fact, many convergence results find their use in theoretical applications, such as Lyapunov stability analysis [1,2,3,4], variational analysis [5,6,7,8,9,10] and game equilibrium seeking [11,12,13,14], in automatic control, such as model predictive control [15] and network control problems [16], as well as in other engineering areas, e.g., training and learning in generative adversarial networks [17,18,19], vehicle flow control in traffic networks [20] and in modeling the prosumer behavior in smart power grids [11,14,21,22].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Convergence of sequences: a survey

Franci¹,

Grammatico²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Convergent sequences of real numbers play a fundamental role in many different problems in system theory, e.g., in Lyapunov stability analysis, as well as in optimization theory and computational game theory. In this survey, we provide an overview of the literature on convergence theorems and their connection with Féjer monotonicity in the deterministic and stochastic settings, and we show how to exploit these results.

show abstract

Section: Lyapunov Decrease and Féjer Monotonicitymentioning

confidence: 99%

Section: Applications Of Convergent Deterministic Sequencesmentioning

confidence: 99%

“…Concerning Nash equilibrium problems, it is used in [11,12,111]. In the specific case of generative adversarial networks, Lemma 4.1 is used in [17,18].…”

Section: Other Applicationsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Convergence of sequences: a survey

Franci¹,

Grammatico²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…It is distinct from the extant results on distributed learning as in References [12–14,18,29,30], where only cooperation among agents exists, while learning for GANs inherently shows its nature of competition. In other words, the existing works 12–14,18 are intrinsically distributed optimisation problems (see References [31–35]) whereas training for GANs in this study is a distributed Nash equilibrium seeking problem with two coalitions (see References [21,23,28,36,37]).…”

Section: Introductionmentioning

confidence: 99%

On the game‐theoretic analysis of distributed generative adversarial networks

Dong

Chen

et al. 2021

Int J Intell Syst

View full text Add to dashboard Cite

In this paper, a distributed method is proposed for training multiple generative adversarial networks (GANs) with private data sets via a game‐theoretic approach. To facilitate the requirement of privacy protection, distributed training algorithms offer a promising solution to learn global models without sample exchanges. Existing studies have mainly concentrated on training neural networks using pure cooperation strategies, which are not suitable for GANs. This paper develops a new framework for distributed GANs, where two groups of discriminators and generators are involved in a zero‐sum game. Under connected graphs, such a framework is reformulated as a constrained minmax optimisation problem. Then, a fully distributed training algorithm is proposed without exchanging any private data samples. The convergence of the proposed algorithm is established via advanced consensus and optimisation techniques. Simulation studies are presented to validate the effectiveness of the proposed framework and algorithm.

show abstract

Machine learning in postgenomic biology and personalized medicine

Ray

2022

WIREs Data Min & Knowl

View full text Add to dashboard Cite

In recent years, machine learning (ML) has been revolutionizing biology, biomedical sciences, and gene‐based agricultural technology capabilities. Massive data generated in biological sciences by rapid and deep gene sequencing and protein or other molecular structure determination, on the one hand, require data analysis capabilities using ML that are distinctly different from classical statistical methods; on the other, these large datasets are enabling the adoption of novel data‐intensive ML algorithms for the solution of biological problems that until recently had relied on mechanistic model‐based approaches that are computationally expensive. This review provides a bird's eye view of the applications of ML in postgenomic biology. Attempt is also made to indicate as far as possible the areas of research that are poised to make further impacts in these areas, including the importance of explainable artificial intelligence in human health. Further contributions of ML are expected to transform medicine, public health, agricultural technology, as well as to provide invaluable gene‐based guidance for the management of complex environments in this age of global warming. This article is categorized under: Technologies > Machine Learning Technologies > Artificial Intelligence Technologies > Prediction

show abstract

A game–theoretic approach for Generative Adversarial Networks

Cited by 8 publications

References 11 publications

Convergence of sequences: a survey

Convergence of sequences: a survey

On the game‐theoretic analysis of distributed generative adversarial networks

Machine learning in postgenomic biology and personalized medicine

Contact Info

Product

Resources

About