Searcharxiv⌕ Search

arXiv subjects

Hamidou Tembine

Publications and source records attributed to Hamidou Tembine.

At least 37 records · Page 2Linked to original sources
arXiv2020

Nonparallel Emotional Speech Conversion

We propose a nonparallel data-driven emotional speech conversion method. It enables the transfer of emotion-related characteristics of a speech signal while preserving the speaker's identity and linguistic content. Most existing approaches require parallel data and time alignment, which is not available in most real applications. We achieve nonparallel training based on an unsupervised style transfer technique, which learns a translation model between two distributions instead of a deterministic one-to-one mapping between paired examples. The conversion model consists of an encoder and a decoder for each emotion domain. We assume that the speech signal can be decomposed into an emotion-invariant content code and an emotion-related style code in latent space. Emotion conversion is performed by extracting and recombining the content code of the source speech and the style code of the target emotion. We tested our method on a nonparallel corpora with four emotions. Both subjective and objective evaluations show the effectiveness of our approach.

cs.LG↗
arXiv2019

Matrix-Valued Mean-Field-Type Games: Risk-Sensitive, Adversarial, and Risk-Neutral Linear-Quadratic Case

In this paper we study a class of matrix-valued linear-quadratic mean-field-type games for both the risk-neutral, risk-sensitive and robust cases. Non-cooperation, full cooperation and adversarial between teams are treated. We provide a semi-explicit solution for both problems by means of a direct method. The state dynamics is described by a matrix-valued linear jump-diffusion-regime switching system of conditional mean-field type where the conditioning is with respect to common noise which is a regime switching process. The optimal strategies are in a state-and-conditional mean-field feedback form. Semi-explicit solutions of equilibrium costs and strategies are also provided for the full cooperative, adversarial teams, risk-sensitive full cooperative and risk-sensitive adversarial team cases. It is shown that full cooperation increases the well-posedness domain under risk-sensitive decision-makers by means of population risk-sharing. Finally, relationship between risk-sensitivity and robustness are established in the mean-field type context.

math.OC↗
arXiv2019

Semi-Explicit Solutions to some Non-Linear Non-Quadratic Mean-Field-Type Games: A Direct Method

This article examines mean-field-type game problems by means of a direct method. We provide various solvable examples beyond the classical linear-quadratic game problems. These include quadratic-quadratic games and games with power, logarithmic, sine square, hyperbolic sine square payoffs. Non-linear state dynamics such as log-state, control-dependent regime switching, quadratic state, cotangent state and hyperbolic cotangent state are considered. We identify equilibrium strategies and equilibrium payoffs in state-and-conditional mean-field type feedback form. It is shown that a simple direct method can be used to solve broader classes of non-quadratic mean-field-type games under jump-diffusion-regime switching Gauss-Volterra processes which include fractional Brownian motions and multi-fractional Brownian motions. We provide semi-explicit solutions to the fully cooperative, noncooperative nonzero-sum, and adversarial game problems.

math.OC↗
arXiv2018

A Stochastic Maximum Principle for Markov chains of mean-field type

We derive sufficient and necessary optimality conditions in terms of a stochastic maximum principle (SMP) for controls associated with cost functionals of mean-field type, under dynamics driven by a class of Markov chains of mean-field type which are pure jump processes obtained as solutions of a well-posed martingale problem. As an illustration, we apply the result to generic examples of control problems as well as some applications.

math.PR↗
arXiv2018

Consensus over evolutionary graphs

We establish average consensus on graphs with dynamic topologies prescribed by evolutionary games among strategic agents. Each agent possesses a private reward function and dynamically decides whether to create new links and/or whether to delete existing ones in a selfish and decentralized fashion, as indicated by a certain randomized mechanism. This model incurs a time-varying and state-dependent graph topology for which traditional consensus analysis is not applicable. We prove asymptotic average consensus almost surely and in mean square for any initial condition and graph topology. In addition, we establish exponential convergence in expectation. Our results are validated via simulation studies on random networks.

math.OC↗
arXiv2017

Mean-Field-Type Games in Engineering

A mean-field-type game is a game in which the instantaneous payoffs and/or the state dynamics functions involve not only the state and the action profile but also the joint distributions of state-action pairs. This article presents some engineering applications of mean-field-type games including road traffic networks, multi-level building evacuation, millimeter wave wireless communications, distributed power networks, virus spread over networks, virtual machine resource management in cloud networks, synchronization of oscillators, energy-efficient buildings, online meeting and mobile crowdsensing.

math.OC↗
arXiv2017

Optimal control and zero-sum games for Markov chains of mean-field type

We establish existence of Markov chains of mean-field type with unbounded jump intensities by means of a fixed point argument using the Total Variation distance. We further show existence of nearly-optimal controls and, using a Markov chain backward SDE approach, we suggest conditions for existence of an optimal control and a saddle-point for respectively a control problem and a zero-sum differential game associated with payoff functionals of mean-field type, under dynamics driven by such Markov chains of mean-field type.

math.OC↗
arXiv2017

Quantile-based Mean-Field Games with Common Noise

In this paper we explore the impact of quantiles on optimal strategies under state dynamics driven by both individual noise, common noise and Poisson jumps. We first establish an optimality system satisfied the quantile process under jump terms. We then turn to investigate a new class of finite horizon mean-field games with common noise in which the payoff functional and the state dynamics are dependent not only on the state-action pair but also on conditional quantiles. Based on the best-response of the decision-makers, it is shown that the equilibrium conditional quantile process satisfies a stochastic partial differential equation in the non-degenerate case. A closed-form expression of the quantile process is provided in a basic Ornstein-Uhlenbeck process with common noise.

math.OC↗
arXiv2017

Empathy in Bimatrix Games

Although the definition of what empathetic preferences exactly are is still evolving, there is a general consensus in the psychology, science and engineering communities that the evolution toward players' behaviors in interactive decision-making problems will be accompanied by the exploitation of their empathy, sympathy, compassion, antipathy, spitefulness, selfishness, altruism, and self-abnegating states in the payoffs. In this article, we study one-shot bimatrix games from a psychological game theory viewpoint. A new empathetic payoff model is calculated to fit empirical observations and both pure and mixed equilibria are investigated. For a realized empathy structure, the bimatrix game is categorized among four generic class of games. Number of interesting results are derived. A notable level of involvement can be observed in the empathetic one-shot game compared the non-empathetic one and this holds even for games with dominated strategies. Partial altruism can help in breaking symmetry, in reducing payoff-inequality and in selecting social welfare and more efficient outcomes. By contrast, partial spite and self-abnegating may worsen payoff equity. Empathetic evolutionary game dynamics are introduced to capture the resulting empathetic evolutionarily stable strategies under wide range of revision protocols including Brown-von Neumann-Nash, Smith, imitation, replicator, and hybrid dynamics. Finally, mutual support and Berge solution are investigated and their connection with empathetic preferences are established. We show that pure altruism is logically inconsistent, only by balancing it with some partial selfishness does it create a consistent psychology.

cs.GT↗
arXiv2017

Distributionally Robust Games: f-Divergence and Learning

In this paper we introduce the novel framework of distributionally robust games. These are multi-player games where each player models the state of nature using a worst-case distribution, also called adversarial distribution. Thus each player's payoff depends on the other players' decisions and on the decision of a virtual player (nature) who selects an adversarial distribution of scenarios. This paper provides three main contributions. Firstly, the distributionally robust game is formulated using the statistical notions of $f$-divergence between two distributions, here represented by the adversarial distribution, and the exact distribution. Secondly, the complexity of the problem is significantly reduced by means of triality theory. Thirdly, stochastic Bregman learning algorithms are proposed to speedup the computation of robust equilibria. Finally, the theoretical findings are illustrated in a convex setting and its limitations are tested with a non-convex non-concave function.

math.OC↗
arXiv2017

Lowest Unique Bid Auctions with Resubmission Opportunities

The recent online platforms propose multiple items for bidding. The state of the art, however, is limited to the analysis of one item auction without resubmission. In this paper we study multi-item lowest unique bid auctions (LUBA) with resubmission in discrete bid spaces under budget constraints. We show that the game does not have pure Bayes-Nash equilibria (except in very special cases). However, at least one mixed Bayes-Nash equilibria exists for arbitrary number of bidders and items. The equilibrium is explicitly computed for two-bidder setup with resubmission possibilities. In the general setting we propose a distributed strategic learning algorithm to approximate equilibria. Computer simulations indicate that the error quickly decays in few number of steps. When the number of bidders per item follows a Poisson distribution, it is shown that the seller can get a non-negligible revenue on several items, and hence making a partial revelation of the true value of the items. Finally, the attitude of the bidders towards the risk is considered. In contrast to risk-neutral agents who bids very small values, the cumulative distribution and the bidding support of risk-sensitive agents are more distributed.

cs.GT↗
arXiv2017

How Much Does Users' Psychology Matter in Engineering Mean-Field-Type Games

Until now mean-field-type game theory was not focused on cognitively-plausible models of choices in humans, animals, machines, robots, software-defined and mobile devices strategic interactions. This work presents some effects of users' psychology in mean-field-type games. In addition to the traditional "material" payoff modelling, psychological patterns are introduced in order to better capture and understand behaviors that are observed in engineering practice or in experimental settings. The psychological payoff value depends upon choices, mean-field states, mean-field actions, empathy and beliefs. It is shown that the affective empathy enforces mean-field equilibrium payoff equity and improves fairness between the players. It establishes equilibrium systems for such interactive decision-making problems. Basic empathy concepts are illustrated in several important problems in engineering including resource sharing, packet collision minimization, energy markets, and forwarding in Device-to-Device communications. The work conducts also an experiment with 47 people who have to decide whether to cooperate or not. The basic Interpersonal Reactivity Index of empathy metrics were used to measure the empathy distribution of each participant. Android app called Empathizer is developed to analyze systematically the data obtained from the participants. The experimental results reveal that the dominated strategies of the classical game theory are not dominated any more when users' psychology is involved, and a significant level of cooperation is observed among the users who are positively partially empathetic.

cs.GT↗
arXiv2017

Empathy in One-Shot Prisoner Dilemma

Strategic decision making involves affective and cognitive functions like reasoning, cognitive and emotional empathy which may be subject to age and gender differences. However, empathy-related changes in strategic decision-making and their relation to age, gender and neuropsychological functions have not been studied widely. In this article, we study a one-shot prisoner dilemma from a psychological game theory viewpoint. Forty seven participants (28 women and 19 men), aged 18 to 42 years, were tested with a empathy questionnaire and a one-shot prisoner dilemma questionnaire comprising a closiness option with the other participant. The percentage of cooperation and defection decisions was analyzed. A new empathetic payoff model was calculated to fit the observations from the test whether multi-dimensional empathy levels matter in the outcome. A significant level of cooperation is observed in the experimental one-shot game. The collected data suggests that perspective taking, empathic concern and fantasy scale are strongly correlated and have an important effect on cooperative decisions. However, their effect in the payoff is not additive. Mixed scales as well as other non-classified subscales (25+8 out of 47) were observed from the data.

cs.GT↗
arXiv2017

Risk-Sensitive Mean-Field-Type Control

We study risk-sensitive optimal control of a stochastic differential equation (SDE) of mean-field type, where the coefficients are allowed to depend on some functional of the law as well as the state and control processes. Moreover the risk-sensitive cost functional is also of mean-field type. We derive optimality equations in infinite dimensions connecting dual functions associated with Bellman functional to the adjoint process of the Pontryagin maximum principle. The case of linear-exponentiated quadratic cost and its connection with the risk-neutral solution is discussed.

math.OC↗
arXiv2016

Deterministic Mean-field Ensemble Kalman Filtering

The proof of convergence of the standard ensemble Kalman filter (EnKF) from Legland etal. (2011) is extended to non-Gaussian state space models. A density-based deterministic approximation of the mean-field limit EnKF (DMFEnKF) is proposed, consisting of a PDE solver and a quadrature rule. Given a certain minimal order of convergence $κ$ between the two, this extends to the deterministic filter approximation, which is therefore asymptotically superior to standard EnKF when the dimension $d<2κ$. The fidelity of approximation of the true distribution is also established using an extension of total variation metric to random measures. This is limited by a Gaussian bias term arising from non-linearity/non-Gaussianity of the model, which exists for both DMFEnKF and standard EnKF. Numerical results support and extend the theory.

math.PR↗
arXiv2016

A Satisfactory Power Control for 5G Self-Organizing Networks

SmallCells are deployed in order to enhance the network performance by bringing the network closer to the user. However, as the number of low power nodes grows increasingly, the overall energy consumption of the SmallCells base stations cannot be ignored. A relevant amount of energy could be saved through several techniques, especially power control mechanisms. In this paper, we are concerned with energy aware self organizing networks that guarantee a satisfactory performance. We consider satisfaction equilibria, mainly the efficient satisfaction equilibrium (ESE), to ensure a target quality of service (QoS) and save energy. First, we identify conditions of existence and uniqueness of ESE under a stationary channel assumption. We fully characterize the ESE and prove that, whenever it exists, it is a solution of a linear system. Moreover, we define satisfactory Pareto optimality and show that, at the ESE, no player can increase its QoS without degrading the overall performance. Under a fast fading channel assumption, as the robust satisfaction equilibrium solution is very restrictive, we propose an alternative solution namely the long term satisfaction equilibrium, and describe how to reach this solution efficiently. Finally, in order to find satisfactory solution per all users, we propose fully distributed strategic learning schemes based on Banach-Picard, Mann and Bush Mosteller algorithms, and show through simulations their qualitative properties. fully distributed strategic learning schemes based on Banach Picard, Mann and Bush Mosteller algorithms, and show through simulations their qualitative properties.

cs.IT↗
arXiv2015

Risk-Sensitive Mean-Field-Type Games with Lp-norm Drifts

We study how risk-sensitive players act in situations where the outcome is influenced not only by the state-action profile but also by the distribution of it. In such interactive decision-making problems, the classical mean-field game framework does not apply. We depart from most of the mean-field games literature by presuming that a decision-maker may include its own-state distribution in its decision. This leads to the class of mean-field-type games. In mean-field-type situations, a single decision-maker may have a big impact on the mean-field terms for which new type of optimality equations are derived. We establish a finite dimensional stochastic maximum principle for mean-field-type games where the drift functions have a p-norm structure which weaken the classical Lipschitz and differentiability assumptions. Sufficient optimality equations are established via Dynamic Programming Principle but in infinite dimension. Using de Finetti-Hewitt-Savage theorem, we show that a propagation of chaos property with 'virtual' particles holds for the non-linear McKean-Vlasov dynamics.

math.OC↗