scholarly journals On Fair Cost Sharing Games in Machine Learning

2019 ◽  
Vol 33 ◽  
pp. 4790-4797
Author(s):  
Ievgen Redko ◽  
Charlotte Laclau
Keyword(s):  
Machine Learning ◽  
Game Theory ◽  
Nash Equilibrium ◽  
Collaborative Learning ◽  
Cost Sharing ◽  
Optimal Solution ◽  
Sample Complexity ◽  
Learning Scenarios ◽  
Theoretical Results ◽  
Optimal Behaviour

Machine learning and game theory are known to exhibit a very strong link as they mutually provide each other with solutions and models allowing to study and analyze the optimal behaviour of a set of agents. In this paper, we take a closer look at a special class of games, known as fair cost sharing games, from a machine learning perspective. We show that this particular kind of games, where agents can choose between selfish behaviour and cooperation with shared costs, has a natural link to several machine learning scenarios including collaborative learning with homogeneous and heterogeneous sources of data. We further demonstrate how the game-theoretical results bounding the ratio between the best Nash equilibrium (or its approximate counterpart) and the optimal solution of a given game can be used to provide the upper bound of the gain achievable by the collaborative learning expressed as the expected risk and the sample complexity for homogeneous and heterogeneous cases, respectively. We believe that the established link can spur many possible future implications for other learning scenarios as well, with privacy-aware learning being among the most noticeable examples.

THE PRICE OF NASH EQUILIBRIA IN MULTICAST TRANSMISSION GAMES

2010 ◽  
Vol 11 (03n04) ◽  
pp. 97-120 ◽  
Author(s):  
VITTORIO BILÒ
Keyword(s):  
Nash Equilibrium ◽  
Cost Sharing ◽  
Price Of Anarchy ◽  
Optimal Solution ◽  
Minimum Cost ◽  
Price Of Stability ◽  
Common Source ◽  
Cost Share ◽  
Worst Case ◽  
The Cost

We consider the problem of sharing the cost of multicast transmissions in non-cooperative undirected networks where a set of receivers R wants to be connected to a common source s. The set of choices available to each receiver r ∈ R is represented by the set of all (s, r)-paths in the network. Given the choices performed by all the receivers, a public known cost sharing method determines the cost share to be charged to each of them. Receivers are selfish agents aiming to obtain the transmission at the minimum cost share and their interactions create a non-cooperative game. Devising cost sharing methods yielding games whose price of anarchy (price of stability), defined as the worst-case (best-case) ratio between the cost of a Nash equilibrium and that of an optimal solution, is not too high is thus of fundamental importance in non-cooperative network design. Moreover, since cost sharing games naturally arise in socio-economical contests, it is convenient for a cost sharing method to meet some constraining properties. In this paper, we first define several such properties and analyze their impact on the prices of anarchy and stability. We also reconsider all the methods known so far by classifying them according to which properties they satisfy and giving the first non-trivial lower bounds on their price of stability. Finally, we propose a new method, namely the free-riders method, which admits a polynomial time algorithm for computing a pure Nash equilibrium whose cost is at most twice the optimal one. Some of the ideas characterizing our approach have been independently proposed in Ref. 10.

scholarly journals Modeling for Driver Decision-Making Behavior during Amber Signal Time at Intersection

2012 ◽  
Vol 5 ◽  
pp. 118-122
Author(s):  
Wei Wei Qi ◽  
Yu Long Pei ◽  
Mo Song
Keyword(s):  
Game Theory ◽  
Nash Equilibrium ◽  
Academic Research ◽  
Optimal Solution ◽  
Warning Signal ◽  
Theory Model ◽  
Operating Efficiency ◽  
Traffic Lights ◽  
Amber Light ◽  
Traffic Conflicts

The current traffic lights are composed of red, amber, and green, and it is controversial that the drivers’ behavior choices and the content of the relevant laws & regulations during the amber timing. From the current situation with the signal intersection, the amber light time and the red clearance aren’t differentiate, usually the amber light time acts as red clearance. It will not improve the traffic operating efficiency of the intersection, but bring more traffic conflicts, if the role of the amber light time returns to academic research, which the amber is a warning signal. The paper analyzes the process that the drivers choose stopping by slowing down or passing by maintaining the speed during amber time from the vehicle dynamic characteristics. And then, the generalized amber interval dilemma is defined to establish the mixed-strategy game theory model, which reveals the utility of the driver and signal manager in the amber interval, and the algorithm of Nash Equilibrium point is also research focus. According to Nash Equilibrium, the optimal solution of the game theory model is (acceleration, amber setting) or (deceleration, amber canceling).

scholarly journals Zen and the art of model adaptation: Low-utility-cost attack mitigations in collaborative machine learning

2021 ◽  
Vol 2022 (1) ◽  
pp. 274-290
Author(s):  
Dmitrii Usynin ◽  
Daniel Rueckert ◽  
Jonathan Passerat-Palmbach ◽  
Georgios Kaissis
Keyword(s):  
Machine Learning ◽  
Collaborative Learning ◽  
Real Life ◽  
Model Adaptation ◽  
Theoretical Understanding ◽  
Model Inversion ◽  
Optimal Balance ◽  
Learning Scenarios ◽  
Utility Cost ◽  
The Impact

Abstract In this study, we aim to bridge the gap between the theoretical understanding of attacks against collaborative machine learning workflows and their practical ramifications by considering the effects of model architecture, learning setting and hyperparameters on the resilience against attacks. We refer to such mitigations as model adaptation. Through extensive experimentation on both, benchmark and real-life datasets, we establish a more practical threat model for collaborative learning scenarios. In particular, we evaluate the impact of model adaptation by implementing a range of attacks belonging to the broader categories of model inversion and membership inference. Our experiments yield two noteworthy outcomes: they demonstrate the difficulty of actually conducting successful attacks under realistic settings when model adaptation is employed and they highlight the challenge inherent in successfully combining model adaptation and formal privacy-preserving techniques to retain the optimal balance between model utility and attack resilience.

scholarly journals Exploring the application of machine learning to the assembly line feeding problem

2021 ◽  
Author(s):  
Moretti Emilio ◽  
Tappia Elena ◽  
Limère Veronique ◽  
Melacini Marco
Keyword(s):  
Machine Learning ◽  
Assembly Line ◽  
Optimal Solution ◽  
Product Variety ◽  
Supervised Machine Learning ◽  
Assembly System ◽  
Optimization Approach ◽  
Feeding Problem ◽  
Managerial Implications ◽  
Multiple Feeding

AbstractAs a large number of companies are resorting to increased product variety and customization, a growing attention is being put on the design and management of part feeding systems. Recent works have proved the effectiveness of hybrid feeding policies, which consist in using multiple feeding policies in the same assembly system. In this context, the assembly line feeding problem (ALFP) refers to the selection of a suitable feeding policy for each part. In literature, the ALFP is addressed either by developing optimization models or by categorizing the parts and assigning these categories to policies based on some characteristics of both the parts and the assembly system. This paper presents a new approach for selecting a suitable feeding policy for each part, based on supervised machine learning. The developed approach is applied to an industrial case and its performance is compared with the one resulting from an optimization approach. The application to the industrial case allows deepening the existing trade-off between efficiency (i.e., amount of data to be collected and dedicated resources) and quality of the ALFP solution (i.e., closeness to the optimal solution), discussing the managerial implications of different ALFP solution approaches and showing the potential value stemming from machine learning application.

scholarly journals Economic Analysis of Accident Law: A New Liability Rule that Induces Socially Optimal Behaviour in Case of Limited Information

2020 ◽  
Vol 0 (0) ◽  
Author(s):  
Astha Srivastava ◽  
Ankur Srivastava
Keyword(s):  
Nash Equilibrium ◽  
Economic Analysis ◽  
Standard Of Care ◽  
Limited Information ◽  
Liability Rule ◽  
Rule Based ◽  
Liability Rules ◽  
Levels Of Care ◽  
Unique Nash Equilibrium ◽  
Optimal Behaviour

AbstractIn accident law, we seek a liability rule that will induce both the parties to adopt socially optimal levels of precaution. Economic analysis, however, shows that none of the commonly used liability rules induce both parties to adopt optimal levels, if courts have access only to ‘Limited Information’ on. In such a case, it has also been established (K. (2006). Efficiency of liability rules: a reconsideration. J. Int. Trade Econ. Dev. 15: 359–373) that no liability rule based on cost justified untaken precaution as a standard of care can be efficient. In this paper, we describe a two-step liability rule: the rule of negligence with the defence of relative negligence. We prove that this rule has a unique Nash equilibrium at socially optimal levels of care for the non-cooperative game, and therefore induces both parties to adopt socially optimal behaviour even in case of limited information.

scholarly journals Holding a group together: non-game-theory vs. game-theory

2021 ◽  
Author(s):  
Michael Richter ◽  
Ariel Rubinstein
Keyword(s):  
Game Theory ◽  
Nash Equilibrium ◽  
Competitive Equilibrium ◽  
Solution Concept ◽  
Equilibrium Concept

Abstract Each member of a group chooses a position and has preferences regarding his chosen position. The group’s harmony depends on the profile of chosen positions meeting a specific condition. We analyse a solution concept (Richter and Rubinstein, 2020) based on a permissible set of individual positions, which plays a role analogous to that of prices in competitive equilibrium. Given the permissible set, members choose their most preferred position. The set is tightened if the chosen positions are inharmonious and relaxed if the restrictions are unnecessary. This new equilibrium concept yields more attractive outcomes than does Nash equilibrium in the corresponding game.

scholarly journals Quantum Mean-Field Games with the Observations of Counting Type

Games ◽  
2021 ◽  
Vol 12 (1) ◽  
pp. 7
Author(s):  
Vassili N. Kolokoltsov
Keyword(s):  
Game Theory ◽  
Nash Equilibrium ◽  
Open Problem ◽  
Existence And Uniqueness ◽  
Existence Of Solutions ◽  
Mean Field ◽  
Mean Field Games ◽  
Quantum Game ◽  
Quantum Games ◽  
Interesting Open Problem

Quantum games and mean-field games (MFG) represent two important new branches of game theory. In a recent paper the author developed quantum MFGs merging these two branches. These quantum MFGs were based on the theory of continuous quantum observations and filtering of diffusive type. In the present paper we develop the analogous quantum MFG theory based on continuous quantum observations and filtering of counting type. However, proving existence and uniqueness of the solutions for resulting limiting forward-backward system based on jump-type processes on manifolds seems to be more complicated than for diffusions. In this paper we only prove that if a solution exists, then it gives an ϵ-Nash equilibrium for the corresponding N-player quantum game. The existence of solutions is suggested as an interesting open problem.

scholarly journals A Survey on Machine Learning and Text Processing for Pesticides and Fertilizer Prediction

2021 ◽  
Vol 12 (2) ◽  
Author(s):  
P.Pandiarajaa , Et. al.
Keyword(s):  
Machine Learning ◽  
New Technologies ◽  
Text Processing ◽  
Disease Incidence ◽  
Optimal Solution ◽  
Paddy Soils ◽  
Advanced Technology ◽  
Sustainable Solutions ◽  
Integrated Research ◽  
Private And Public

In the Agriculture sectors the pressure is increased immensely due to the rise in population. In this present year we mainly witness a move from conventional methods to the advanced technology with advent of the technology. Machine Learning and Text Processing have transformed the quality and the quantity of agriculture. The real time monitoring systems along with hybridization of species paved away for resource efficiency. Scientists and researchers across the globe are mainly shifting towards collaborative projects and ideologies to explore this field for saving society. The optimal solution has been provided by racing in the tech industry. This application will be portable, scalable and durable that provides help for initiating new areas in the agriculture field. So, this survey focuses on machine learning methodologies along with Text Processing systems in agriculture. This startup’s private and public sector which is around the world that provides smart and sustainable solutions are briefly discussed. Based on agriculture this scenario, limitations, applications, development and future parameters are also briefly explained. The greatest challenge for the future agriculture lies in making agriculture research and extension more demand driven and client oriented. In addition, laboratory analysis has been undertaken to assess the nitrogen status and the soil carbon of fresh paddy soils and the used paddy soils as well as saplings. During the first season of 2011 the data collected on pests, disease incidence and severity and yield are being compiled for analysis. Therefore, integrated research to develop a bottom up participatory technology extension approach using new technologies is suggested for sustainable development in agriculture.

scholarly journals Linear programming measures for solving the problem of a linear division of convex multiplayers.

2018 ◽  
Vol 10 (2) ◽  
Author(s):  
Sarmad H. Ali ◽  
Osamah A. Ali ◽  
Samir C. Ajmi
Keyword(s):  
Machine Learning ◽  
Linear Programming ◽  
Optimal Solution ◽  
Optimal Method ◽  
Linear Separation ◽  
Different Types ◽  
Simplex Methods

In this research, we are trying to solve Simplex methods which are used for successively improving solution and finding the optimal solution, by using different types of methods Linear, the concept of linear separation is widely used in the study of machine learning, through this study we will find the optimal method to solve by comparing the time consumed by both Quadric and Fisher methods.

Sign in / Sign up

Export Citation Format

Share Document