No description available.

Formulating consistent marketing strategies is a difficult task, but successfully implementing them is even more challenging. This is even more pertinent as marketing strategies quite often incorporate inherent conflicts between major breakthroughs and consolidation. Consequently, marketers need to balance exploratory and exploitative strategies. However, the literature lacks concrete insights for marketing managers as to how exploratory and exploitative strategies can be best combined. This paper addresses this issue by introducing a framework of multiple types of ambidexterity. Based on qualitative research, tools and procedures are identified to overcome marketing dilemmas and support strategy implementation by drawing on ambidextrous designs. (authors' abstract)

To align firm strategy with the changing environment has always been a challenge for executives. The business literature consists of different perspectives on how to solve the problem and whether to resist change, adapt or do both at the same time. Each got their own implications, inertia could lead to rigidness, adaptability might negatively influence reliability and ambidexterity is seen as a combination of both. The core is exploiting present capabilities meanwhile exploring future opportunities. To study these notions we have conducted a cross-sectional study including four Swedish service-firms which operates in either a stable or dynamic environment. Executives were interviewed and asked to elaborate on their strategies. By doing this we were able to construct a model who suggests when to adapt, when to resist change depending on environmental stability. We also observed that capital- and knowledge-intensity has been somewhat neglected in previous research and could be studied further.

京都大学 / 新制・課程博士 / 博士(人間・環境学) / 甲第23270号 / 人博第985号 / 新制||人||233(附属図書館) / 2020||人博||985(吉田南総合図書館) / 京都大学大学院人間・環境学研究科共生人間学専攻 / (主査)教授 内田 由紀子, 教授 齋木 潤, 教授 月浦 崇 / 学位規則第4条第1項該当 / Doctor of Human and Environmental Studies / Kyoto University / DGAM

No description available.

Une question fondamentale en neuroscience, ainsi que dans de nombreuses disciplines s’intéressant à la compréhension du comportement, telles que la psychologie, l’Economie, et la sociologie, concerne les processus décisionnels par lesquels les animaux et les humains sélectionnent des actions renforcées positivement ou négativement. Les processus décisionnels ainsi que leur base neuronale demeurent mal compris. D’autre part de nombreuses études ont révélé que les humains ainsi que les animaux prennent souvent des décisions sous-optimales. Notre principal objectif a été de comprendre la raison de ces comportements sous-optimaux. Par ailleurs, l’altération des processus sous-tendant la prise de décision, entraîne des pathologies. La compréhension des mécanismes décisionnels est essentielle au développement de stratégies de traitements plus efficaces. Dans cette étude nous avons proposé une nouvelle approche de l’étude des comportements décisionnels, basée sur l’hétérogénéité des préférences créées au cours de l’apprentissage du choix. Puis nous avons corrélé l’activité du putamen et du globus pallidus interne aux comportements préalablement décrits. Nos résultats montrent que bien que les primates apprennent à identifier la meilleure option et convergent vers une stratégie optimale dans un nombre important de sessions, ils n’arrivent pas en moyenne à optimiser leur comportement. Nous avons montré que ce comportement suboptimal des primates est caractérisé par la création de préférences irrationnelles par ces derniers pour des paramètres non pertinents de l’environnement. Nous avons finalement montré que bien qu’un faible nombre de neurones du putamen encode la valeur de l’action, leur contribution à l’activité de population est faible. L’activité du putamen reflète les futures performances des primates et prédit donc la formation des comportements irrationnels et rationnels. / A fundamental question in neuroscience, as well as in various fields such as economics, psychology and sociology, concerns the decision making processes by which animals and humans select actions based on reward and punishment. Both decision making processes and their neural basis are still poorly understood. Also, both human and animals often make suboptimal decisions in many tasks studied. Our first aim is to improve the understanding of why such sub-optimal decisions are made. Also, the alteration of decision making processes causes diseases, the understanding of whose mechanisms is essential in developing better treatment strategies. In this report, we propose a new approach which consists in extracting the neural substrates of choice behavior heterogeneity in between sessions. Our results show that although primates learn on average to identify the best option and converge to an optimal policy in a consequent number of sessions, they fail on average to optimize their behavior. We revealed that this suboptimal behavior was characterized by an unexpected high behavioral heterogeneity during the task that was due to the creation of irrelevant preferences by the monkeys. We finally show that although a few neurons of the putamen encode the action value, their contribution to the overall population activity is weak. Putamen activity rather reflects the futures performances and predicts the creation of rational and irrational behaviors.

The purpose of this dissertation is to understand how algorithms can efficiently learn to solve new tasks based on previous experience, instead of being explicitly programmed with a solution for each task that we want it to solve. Here a task is a series of decisions, such as a robot vacuum deciding which room to clean next or an intelligent car deciding to stop at a traffic light. In such a case, state-of-the-art learning algorithms are difficult to employ in practice because they often make thou- sands of mistakes before reliably solving a task. However, humans learn solutions to novel tasks, often making fewer mistakes, which suggests that efficient learning algorithms may exist. One advantage that humans have over state- of-the-art learning algorithms is that, while learning a new task, humans can apply knowledge gained from previously solved tasks. The central hypothesis investigated by this dissertation is that learning algorithms can solve new tasks more efficiently when they take into consideration knowledge learned from solving previous tasks. Al- though this hypothesis may appear to be obviously true, what knowledge to use and how to apply that knowledge to new tasks is a challenging, open research problem. I investigate this hypothesis in three ways. First, I developed a new learning algorithm that is able to use prior knowledge to constrain the exploration space. Second, I extended a powerful theoretical framework in machine learning, called Probably Approximately Correct, so that I can formally compare the efficiency of algorithms that solve only a single task to algorithms that consider knowledge from previously solved tasks. With this framework, I found sufficient conditions for using knowledge from previous tasks to improve efficiency of learning to solve new tasks and also identified conditions where transferring knowledge may impede learning. I present situations where transfer learning can be used to intelligently constrain the exploration space so that optimality loss can be minimized. Finally, I tested the efficiency of my algorithms in various experimental domains. These theoretical and empirical results provide support for my central hypothesis. The theory and experiments of this dissertation provide a deeper understanding of what makes a learning algorithm efficient so that it can be widely used in practice. Finally, these results also contribute the general goal of creating autonomous machines that can be reliably employed to solve complex tasks.

La prise de décision est un domaine très étudié en sciences, que ce soit en neurosciences pour comprendre les processus sous tendant la prise de décision chez les animaux, qu’en robotique pour modéliser des processus de prise de décision efficaces et rapides dans des tâches en environnement réel. En neurosciences, ce problème est résolu online avec des modèles de prises de décision séquentiels basés sur l’apprentissage par renforcement. En robotique, l’objectif premier est l’efficacité, dans le but d’être déployés en environnement réel. Cependant en robotique ce que l’on peut appeler le budget et qui concerne les limitations inhérentes au matériel, comme les temps de calculs, les actions limitées disponibles au robot ou la durée de vie de la batterie du robot, ne sont souvent pas prises en compte à l’heure actuelle. Nous nous proposons dans ce travail de thèse d’introduire la notion de budget comme contrainte explicite dans les processus d’apprentissage robotique appliqués à une tâche de localisation en mettant en place un modèle basé sur des travaux développés en apprentissage statistique qui traitent les données sous contrainte de budget, en limitant l’apport en données ou en posant une contrainte de temps plus explicite. Dans le but d’envisager un fonctionnement online de ce type d’algorithmes d’apprentissage budgétisé, nous discutons aussi certaines inspirations possibles qui pourraient être prises du côté des neurosciences computationnelles. Dans ce cadre, l’alternance entre recherche d’information pour la localisation et la décision de se déplacer pour un robot peuvent être indirectement liés à la notion de compromis exploration-exploitation. Nous présentons notre contribution à la modélisation de ce compromis chez l’animal dans une tâche non stationnaire impliquant différents niveaux d’incertitude, et faisons le lien avec les méthodes de bandits manchot. / Decision-making is a highly researched field in science, be it in neuroscience to understand the processes underlying animal decision-making, or in robotics to model efficient and rapid decision-making processes in real environments. In neuroscience, this problem is resolved online with sequential decision-making models based on reinforcement learning. In robotics, the primary objective is efficiency, in order to be deployed in real environments. However, in robotics what can be called the budget and which concerns the limitations inherent to the hardware, such as computation times, limited actions available to the robot or the lifetime of the robot battery, are often not taken into account at the present time. We propose in this thesis to introduce the notion of budget as an explicit constraint in the robotic learning processes applied to a localization task by implementing a model based on work developed in statistical learning that processes data under explicit constraints, limiting the input of data or imposing a more explicit time constraint. In order to discuss an online functioning of this type of budgeted learning algorithms, we also discuss some possible inspirations that could be taken on the side of computational neuroscience. In this context, the alternation between information retrieval for location and the decision to move for a robot may be indirectly linked to the notion of exploration-exploitation compromise. We present our contribution to the modeling of this compromise in animals in a non-stationary task involving different levels of uncertainty, and we make the link with the methods of multi-armed bandits.

No description available.

The distributed nature of Federated Learning (FL) creates security-related vulnerabilities including training-time attacks. Recently, it has been shown that well-known Byzantine-resilient aggregation schemes are indeed vulnerable to an informed adversary who has access to the aggregation scheme and updates sent by clients. Therefore, it is a significant challenge to establish successful defense mechanisms against such an adversary. To the best of our knowledge, most current aggregators are immune to single or partial attacks and none of them is expandable to defend against new attacks. We frame the robust distributed learning problem as a game between a server and an adversary that tailors training-time attacks. We introduce RobustTailor, a simulation-based algorithm that prevents the adversary from being omniscient. RobustTailor is a mixed strategy and has good expandability for any deterministic Byzantine-resilient algorithm. Under a challenging setting with information asymmetry between two players, we show that our method enjoys theoretical guarantees in terms of regret bounds. RobustTailor preserves almost the same privacy guarantees as standard FL and robust aggregation schemes. Simulation improves robustness to training-time attacks significantly. Empirical results under challenging attacks validate our theory and show that RobustTailor preforms similar to an upper bound which assumes the server has perfect knowledge of all honest clients over the course of training. / Den distribuerade karaktären hos federerade maskininlärnings-system gör dem sårbara för cyberattacker, speciellt under tiden då systemen tränas. Nyligen har det visats att många existerande Byzantine-resilienta aggregeringssystem är sårbara för attacker från en välinformerad motståndare som har tillgång till aggregeringssystemet och uppdateringarna som skickas av klienterna. Det är därför en stor utmaning att skapa framgångsrika försvarsmekanismer mot en sådan motståndare. Såvitt vi vet är de flesta nuvarande aggregatorer immuna mot enstaka eller partiella attacker och ingen av dem kan på ett enkelt sätt utvidgas för att försvara sig mot nya attacker. Vi utformar det robusta distribuerade inlärningsproblemet som ett spel mellan en server och en motståndare som skräddarsyr attacker under träningstiden. Vi introducerar RobustTailor, en simuleringsbaserad algoritm som förhindrar att motståndaren är allvetande. RobustTailor är en blandad strategi med god expanderbarhet för alla deterministiska Byzantine-resilienta algoritmer. I en utmanande miljö med informationsasymmetri mellan de två spelarna visar vi att vår metod har teoretiska garantier i form av gränser för ånger. RobustTailor har nästan samma integritetsgarantier som standardiserade federerade inlärnings- och robusta aggregeringssystem. Vi illustrerar även hur simulering förbättrar robustheten mot attacker under träningstiden avsevärt. Empiriska resultat vid utmanande attacker bekräftar vår teori och visar att RobustTailor presterar på samma sätt som en övre gräns som förutsätter att servern har perfekt kunskap om alla ärliga klienter under utbildningens gång.