The Randomized Gauss-Seidel Method (RGS) is an iterative algorithm that solves overdetermined systems of linear equations Ax = b. This paper studies an update on the RGS method, the Randomized Block Gauss-Seidel Method. At each step, the algorithm greedily minimizes the objective function L(x) = kAx bk2 with respect to a subset of coordinates. This paper describes a Randomized Block Gauss-Seidel Method (RBGS) which uses a randomized control method to choose a subset at each step. This algorithm is the first block RGS method with an expected linear convergence rate which can be described by the properties of the matrix A and its column submatrices. The analysis demonstrates that RBGS improves RGS more when given appropriate column-paving of the matrix, a partition of the columns into well-conditioned blocks. The main result yields a RBGS method that is more e cient than the simple RGS method.

The Bogoliubov theory of excitations in superfluid helium is used to study collective modes at zero temperature. A repulsive delta function shell potential is used in the quasiparticle excitation energy spectrum to fit the observed elementary excitation spectrum, except in the plateau region. The linearized equation of motion method is used to obtain the secular equation for a collective mode consisting of a linear combination of one and two free quasiparticles of zero total momentum. It is shown that in this case for high-lying collective modes, vertices involving three quasiparticles cancel, and only vertices involving four quasiparticles are important. A decomposition into various angular momentum states is then made. Bound roton pairs in the angular momentum D-state observed in light-scattering experiments exist only for an attractive coupling between helium atoms in this oversimplified model. Thus, the interaction between particles can be reinterpreted as a phenomenological attractive coupling between quasiparticles, in order to explain the Raman scattering from bound roton pairs in superfluid helium.

Biodiesel and hydrotreated vegetable oil (HVO) are currently viewed by the transportation sector as the most viable alternative fuels to replace petroleum-based fuels. The use of biodiesel has, however, been limited by the deteriorative effect of biodiesel on rubber parts in automobile fuel systems. This work therefore aimed at investigating the degradation of acrylonitrile butadiene rubber (NBR) and fluoroelastomers (FKM) on exposure to biodiesel and HVO at different temperatures and oxygen concentrations in an automated ageing equipment and a high-pressure autoclave. The oxidation of biodiesel at 80 °C was promoted by an increase in the oxygen partial pressure, resulting in the formation of larger amounts of hydroperoxides and acids in the fuel. The fatty acid methyl esters of the biodiesel oxidized less at 150 °C on autoclave aging, because the termination reactions between alkyl and alkylperoxyl radicals dominated over the initiation reactions. HVO consists of saturated hydrocarbons, and remained intact during the exposure. The NBR absorbed a large amount of biodiesel due to fuel-driven internal cavitation in the rubber, and the uptake increased with increasing oxygen partial pressure due to the increase in concentration of oxidation products of the biodiesel. The absence of a tan δ peak (dynamical mechanical measurements) of the bound rubber and the appearance of carbon black particles devoid of rubber suggested that the cavitation was caused by the detachment of bound rubber from particle surfaces. A significant decrease in the strain-at-break and in the Payne-effect amplitude of NBR exposed to biodiesel was explained as being due to the damage caused by biodiesel to the rubber-carbon-black network. During the high-temperature autoclave ageing, the NBR swelled less in biodiesel, and showed a small decrease in the strain-at-break due to the cleavage of rubber chains. The degradation of NBR in the absence of carbon black was due only to biodiesel-promoted oxidative crosslinking. The zinc cations released by the dissolution of zinc oxide particles in biodiesel promoted reduction reactions in the acrylonitrile part of the NBR. Heat-treated star-shaped ZnO particles dissolved more slowly in biodiesel than the commercial ZnO nanoparticles due to the elimination of inter-particle porosity by heat treatment. The fuel sorption was hindered in HVO-exposed NBR by the steric constraints of the bulky HVO molecules. The extensibility of NBR decreased only slightly after exposure to HVO, due to the migration of plasticizer from the rubber. The bisphenol-cured FKM co- and terpolymer swelled more than the peroxide-cured GFLT-type FKM in biodiesel due to the chain cleavage caused by the attack of biodiesel on the double bonds formed during the bisphenol curing. The FKM rubbers absorbed biodiesel faster, and to a greater extent, with increasing oxygen concentration. It is suggested that the extensive biodiesel uptake and the decrease in the strain-at-break and Young’s modulus of the FKM terpolymer was due to dehydrofluorination of the rubber by the coordination complexes of biodiesel and magnesium oxide and calcium hydroxide particles. An increase in the CH2-concentration of the extracted FKM rubbers suggested that biodiesel was grafted onto the FKM at the unsaturated sites resulting from dehydrofluorination. / <p>QC 20170227</p>

This work investigates the international spillover effects and transmission channels of Unconventional Monetary Policy (UMP) of major central banks from United States, United Kingdom, Japan and Europe to Latin-American countries. A Global VAR model is estimated to analyze the impact on output, inflation, credit, equity prices and money growth on the selected countries. Results suggest that indeed, there are international spillovers to the region with money growth, stock prices and international reserves as the main transmission channels. In addition, outcomes are different between countries and variables implying not only that transmission channels are not same across the region but also that the effects of the monetary policy are not distributed equally. Furthermore, it is found evidence that for some countries transmission channels may have transformed due to the crisis. Finally, effects of UMP during the crisis were in general positive with exception of Japan indicating that policies from this country brought more costs than benefits to the region. Keywords Zero Lower Bound, Unconventional Monetary Policy, International Spillovers, Global VAR, GVAR.

We present an analysis framework for performance evaluation of large-scale resource-bound (LSRB) computer systems. LSRB systems are those whose resources are continually in demand to serve resource users, who appear in large populations and cause high contention. In these systems, the delivery of quality service is crucial, even in the event of resource failure. Therefore, various techniques have been developed for evaluating their performance. In this thesis, we focus on the technique of quantitative modelling, where in order to study a system, first its model is constructed and then the system’s behaviour is analysed via the model. A number of high level formalisms have been developed to aid the task of model construction. We focus on PEPA, a stochastic process algebra that supports compositionality and enables us to easily build complex LSRB models. In spite of this advantage, however, the task of analysing LSRB models still poses unresolved challenges. LSRB models give rise to very large state spaces. This issue, known as the state space explosion problem, renders the techniques based on discrete state representation, such as numerical Markovian analysis, computationally expensive. Moreover, simulation techniques, such as Gillespie’s stochastic simulation algorithm, are also computationally demanding, as numerous trajectories need to be collected. Furthermore, as we show in our first contribution, the techniques based on the mean-field theory or fluid flow approximation are not readily applicable to this case. In LSRB models, resources are not assumed to be present in large populations and models exhibit highly noisy and stochastic behaviour. Thus, the mean-field deterministic behaviour might not be faithful in capturing the system’s randomness and is potentially too crude to show important aspects of their behaviours. In this case, the modeller is unable to obtain important performance indicators, such as the reliability measures of the system. Considering these limitations, we contribute the following analytical methods particularly tailored to LSRB models. First, we present an aggregation method. The aggregated model captures the evolution of only the system’s resources and allows us to efficiently derive a probability distribution over the configurations they experience. This distribution provides full faithfulness for studying the stochastic behaviour of resources. The aggregation can be applied to all LSRB models that satisfy a syntactic aggregation condition, which can be quickly checked syntactically. We present an algorithm to generate the aggregated model from the original model when this condition is satisfied. Second, we present a procedure to efficiently detect time-scale near-complete decomposability (TSND). The method of TSND allows us to analyse LSRB models at a reduced cost, by dividing their state spaces into loosely coupled blocks. However, one important input is a partition of the transitions defined in the model, categorising them into slow or fast. Forming the necessary partition by the analysis of the model’s complete state space is costly. Our process derives this partition efficiently, by relying on a theorem stating that our aggregation preserves the original model’s partition and therefore, it can be derived by an efficient reachability analysis on the aggregated state space. We also propose a clustering algorithm to implement this reachability analysis. Third, we present the method of conditional moments (MCM) to be used on LSRB models. Using our aggregation, a probability distribution is formed over the configurations of a model’s resources. The MCM outputs the time evolution of the conditional moments of the marginal distribution over resource users given the configurations of resources. Essentially, for each such configuration, we derive measures such as conditional expectation, conditional variance, etc. related to the dynamics of users. This method has a high degree of faithfulness and allows us to capture the impact of the randomness of the behaviour of resources on the users. Finally, we present the advantage of the methods we proposed in the context of a case study, which concerns the performance evaluation of a two-tier wireless network constructed based on the femto-cell macro-cell architecture.

Les méthodes de trajectographie conventionnelles par mesures d’angle supposent que la source est en mouvement rectiligne uniforme tandis que l’observateur est manœuvrant. Dans cette thèse, nous remettons en cause cette hypothèse en proposant un autre modèle de cinématique de la source : le mouvement circulaire uniforme. Nous prouvons qu’une telle trajectoire est observable à partir d’un observateur en mouvement rectiligne uniforme. Puis, nous étudions l’apport de mesures additionnelles de fréquence ou la faisabilité de la trajectographie par mesures de distances. Le cas d’une source en mouvement rectiligne uniforme et d’un observateur manœuvrant est étudié pour ce dernier type de mesures. Chaque cas donne lieu à une analyse de l’observabilité de la trajectoire de la source et à la mise au point de l’estimateur du maximum de vraisemblance. Nous montrons que ce dernier s’avère le plus souvent efficace. / The conventional bearings-only target motion analysis methods assume that the source is in constant velocity motion (constant speed and heading) while the observer maneuvers. In this thesis, we reassess this hypothesis and propose another model of the kinematics of the source: the constant turn motion (an arc of circle followed at constant speed). We prove that this kind of trajectory is observable by an observer in constant velocity motion. Then, we study the contribution of the addition of frequency measurements or the feasibility of target motion analysis methods that use range only measurements. The case of a source in constant velocity motion with a maneuvering observer is examined for this last type of measurements. Each case leads to an analysis of the observability of the trajectory of the source and to the development of the associated maximum likelihood estimator. We show that this estimator often appears to be efficient.

O objetivo deste trabalho visa a prática da psicanálise lacaniana e sua fundamentação, tendo a civilização como parceira. Os impasses da civilização do risco e suas incidências sobre o corpo interessam-nos como viés para uma reflexão sobre a prática da psicanálise lacaniana na atualidade, especialmente em sua relação com os novos sintomas, sobretudo a partir do início do séc. XXI. O interesse em dialogar com a contemporaneidade visa fundamentar ainda mais a experiência da psicanálise aplicada, razão da forte presença dos psicanalistas nas instituições. Não nos detivemos apenas em aspectos da contemporaneidade. Para melhor situar na prática lacaniana a noção de falasser [parlêtre], a partir do último ensino de Lacan, resgatamos o debate sobre os universais, a aposta de Pascal e o mito hegeliano do senhor/mestre e do escravo. / This paper is related to the Lacanian psychoanalytical practice and its theoretical fundaments based on civilization as support . Civilization impasses on risk and their incidences on the body are considered as they lead to a reflection about the practice of Lacanian psychoanalysis in our days, especially when new symptoms are concerned, since the beginning of the 21st century. The interest in sustaining, with our contemporary times, a dialogue aims to add fundaments to applied psychoanalysis, considering the relevant presence of psychoanalysts in the institutions. This paper is nor more limited to what is found in contemporary times to better situate, in the Lacanian practice, the concept of parlêtre (by letter made) from Lacans last teaching. We have also recovered the debate about universals, Pascals bet and the Hegelian myth about the master and the slave.

Thesis advisor: Susanto Basu / The Great Recession is arguably the most important macroeconomic event of the last three decades. Prior to the collapse of national output during 2008 and 2009, the United States experienced a sustained period of good economic outcomes with only two mild and short recessions. In addition to the severity of the recession, several characteristics of this recession signify it as as a unique event in the recent economic history of the United States. Some of these unique features include the following: Large Increase in Uncertainty About the Future: The Great Recession and its subsequent slow recovery have been marked by a large increase in uncertainty about the future. Uncertainty, as measured by the VIX index of implied stock market volatility, peaked at the end of 2008 and has remained volatile over the past few years. Many economists and the financial press believe the large increase in uncertainty may have played a role in the Great Recession and subsequent slow recovery. For example, Kocherlakota (2010) states, ``I've been emphasizing uncertainties in the labor market. More generally, I believe that overall uncertainty is a large drag on the economic recovery.'' In addition, Nobel laureate economist Peter Diamond argues, ``What's critical right now is not the functioning of the labor market, but the limits on the demand for labor coming from the great caution on the side of both consumers and firms because of the great uncertainty of what's going to happen next.'' Zero Bound on Nominal Interest Rates: The Federal Reserve plays a key role in offsetting the negative impact of fluctuations in the economy. During normal times, the central bank typically lowers nominal short-term interest rates in response to declines in inflation and output. Since the end of 2008, however, the Federal Reserve has been unable to lower its nominal policy rate due to the zero lower bound on nominal interest rates. Prior to the Great Recession, the Federal Reserve had not encountered the zero lower bound in the modern post-war period. The zero lower bound represents a significant constraint monetary policy's ability to fully stabilize the economy. Unprecedented Use of Forward Guidance: Even though the Federal Reserve remains constrained by the zero lower bound, the monetary authority can still affect the economy through expectations about future nominal policy rates. By providing agents in the economy with forward guidance on the future path of policy rates, monetary policy can stimulate the economy even when current policy rates remain constrained. Throughout the Great Recession and the subsequent recovery, the Federal Reserve provided the economy with explicit statements about the future path of monetary policy. In particular, the central bank has discussed the timing and macroeconomic conditions necessary to begin raising its nominal policy rate. Using this policy tool, the Federal Reserve continues to respond to the state of the economy at the zero lower bound. Large Fiscal Expansion: During the Great Recession, the United States engaged in a very large program of government spending and tax reductions. The massive fiscal expansion was designed to raise national income and help mitigate the severe economic contraction. A common justification for the fiscal expansion is the reduced capacity of the monetary authority to stimulate the economy at the zero lower bound. Many economists argue that the benefits of increasing government spending are significantly higher when the monetary authority is constrained by the zero lower bound. The goal of this dissertation is to better understand how these various elements contributed to the macroeconomic outcomes during and after the Great Recession. In addition to understanding each of the elements above in isolation, a key component of this analysis focuses on the interaction between the above elements. A key unifying theme between all of the elements is the role in monetary policy. In modern models of the macroeconomy, the monetary authority is crucial in determining how a particular economic mechanism affects the macroeconomy. In the first and second chapters, I show that monetary policy plays a key role in offsetting the negative effects of increased uncertainty about the future. My third chapter highlights how assumptions about monetary policy can change the impact of various shocks and policy interventions. For example, suppose the fiscal authority wants to increase national output by increasing government spending. A key calculation in this situation is the fiscal multiplier, which is dollar increase in national income for each dollar of government spending. I show that fiscal multipliers are dramatically affected by the assumptions about monetary policy even if the monetary authority is constrained by the zero lower bound. The unique nature of the elements discussed above makes analyzing their contribution difficult using standard macroeconomic tools. The most popular method for analyzing dynamic, stochastic general equilibrium models of the macroeconomy relies on linearizing the model around its deterministic steady state and examining the local dynamics around that approximation. However, the nature of the unique elements above make it impossible to fully capture dynamics using local linearization methods. For example, the zero lower bound on nominal interest rates often occurs far from the deterministic steady state of the model. Therefore, linearization around the steady state cannot capture the dynamics associated with the zero lower bound. The overall goal of this dissertation is to use and develop tools in computational macroeconomics to help better understand the Great Recession. Each of the chapters outlined below examine at least one of the topics listed above and its impact in explaining the macroeconomics of the Great Recession. In particular, the essays highlight the role of the monetary authority in generating the observed macroeconomic outcomes over the past several years. Can increased uncertainty about the future cause a contraction in output and its components? In joint work with Susanto Basu, my first chapter examines the role of uncertainty shocks in a one-sector, representative-agent, dynamic, stochastic general-equilibrium model. When prices are flexible, uncertainty shocks are not capable of producing business-cycle comovements among key macroeconomic variables. With countercyclical markups through sticky prices, however, uncertainty shocks can generate fluctuations that are consistent with business cycles. Monetary policy usually plays a key role in offsetting the negative impact of uncertainty shocks. If the central bank is constrained by the zero lower bound, then monetary policy can no longer perform its usual stabilizing function and higher uncertainty has even more negative effects on the economy. We calibrate the size of uncertainty shocks using fluctuations in the VIX and find that increased uncertainty about the future may indeed have played a significant role in worsening the Great Recession, which is consistent with statements by policymakers, economists, and the financial press. In sole-authored work, the second chapter continues to explore the interactions between the zero lower bound and increased uncertainty about the future. From a positive perspective, the essay further shows why increased uncertainty about the future can reduce a central bank's ability to stabilize the economy. The inability to offset contractionary shocks at the zero lower bound endogenously generates downside risk for the economy. This increase in risk induces precautionary saving by households, which causes larger contractions in output and inflation and prolongs the zero lower bound episode. The essay also examines the normative implications of uncertainty and shows how monetary policy can attenuate the negative effects of higher uncertainty. When the economy faces significant uncertainty, optimal monetary policy implies further lowering real rates by committing to a higher price-level target. Under optimal policy, the monetary authority accepts higher inflation risk in the future to minimize downside risk when the economy hits the zero lower bound. In the face of large shocks, raising the central bank's inflation target can attenuate much of the downside risk posed by the zero lower bound. In my third chapter, I examine how assumptions about monetary policy affect the economy at the zero lower bound. Even when current policy rates are zero, I argue that assumptions regarding the future conduct of monetary policy are crucial in determining the effects of real fluctuations at the zero lower bound. Under standard Taylor (1993)-type policy rules, government spending multipliers are large, improvements in technology cause large contractions in output, and structural reforms that decrease firm market power are bad for the economy. However, these policy rules imply that the central bank stops responding to the economy at the zero lower bound. This assumption is inconsistent with recent statements and actions by monetary policymakers. If monetary policy endogenously responds to current economic conditions using expectations about future policy, then spending multipliers are much smaller and increases in technology and firm competitiveness remain expansionary. Thus, the model-implied benefits of higher government spending are highly sensitive to the specification of monetary policy. / Thesis (PhD) — Boston College, 2014. / Submitted to: Boston College. Graduate School of Arts and Sciences. / Discipline: Economics.

Thesis advisor: Peter Ireland / A significant theoretical literature suggests that the effects of open market operations and large scale asset purchases are limited when short-term interest rates are constrained by the zero-lower-bound (ZLB). This view is supported by a growing body of empirical evidence that points to the tepid response of the U.S. economy to extraordinary policy measures implemented by the Federal Reserve (Fed) during the past several years. In the first essay, Effective Monetary Policy at the Zero-Lower-Bound, I show that permanent open market operations (POMOs), defined as financial market interventions that permanently increase the supply of money, remain relevant at the ZLB and can increase output and inflation. Consequently, I argue that the limited success of Fed policy in recent years may be due in part to the fact that it failed to generate sufficient money creation to support economic recovery following the Great Recession. I then demonstrate that conducting POMOs at the ZLB may improve welfare when compared to a broad range of policy regimes, and conclude by conducting a robustness exercise to illustrate that money creation remains relevant at the ZLB when it is not necessarily permanent. With these results in hand, I explore the consequences of Fed QE more directly in a framework asset purchases are an independent instrument of monetary policy. In the second essay, Effective Quantitative Easing at the Zero-Lower-Bound, I show that the observed lack of transmission between U.S. monetary policy and output economic activity a consequence of the fact the Fed engaged in what I define as sterilized QE: temporary asset purchases that have a limited effect on the money supply. Conversely, I show that asset purchase programs geared towards generating sustained increases in the money supply may significantly attenuate output and inflation losses associated with adverse economic shocks and the ZLB constraint. Furthermore, these equilibrium outcomes may be achieved with a smaller volume of asset purchases. My results imply that Fed asset purchase programs designed to offset the observed declines in the U.S. money supply could have been a more effective and efficient means of providing economic stimulus during the recovery from the Great Recession. The third essay—which is joint work with Apollon Fragkiskos, Harold Spilker, and Russ Wermers— titled Buyout Gold: MIDAS Estimators and Private Equity, we develop a new approach to study private equity returns using a data set first introduced in Fragkiskos et al. (2017). Our innovation is that we adopt a mixed data sampling (MIDAS) framework and model quarterly private equity returns as a function of high frequency factor prices. This approach allows us to endogenize time aggregation and use within-period information that may be relevant to pricing private equity returns in a single, parsimonious framework. We find that our MIDAS framework offers superior performance in terms of generating economically meaningful factor loadings and in-sample and out-of-sample fit using index and vintage-level returns when compared with other methods from the literature. Results using fund-level data are mixed, but MIDAS does display a slight edge. Concerning appropriate time-aggregation, we show that there is significant heterogeneity at the vintage level. This implies highly aggregated private equity data may not properly reflect underlying performance in the cross section.

Cette thèse étudie les techniques de gestion intelligente du spectre et de topologie des réseaux via une approche radio intelligente dans le but d’améliorer leur capacité, leur qualité de service (QoS – Quality of Service) et leur consommation énergétique. Les techniques d’apprentissage par renforcement y sont utilisées dans le but d’améliorer les performances d’un système radio intelligent. Dans ce manuscrit, nous traitons du problème d’accès opportuniste au spectre dans le cas de réseaux intelligents sans infrastructure. Nous nous plaçons dans le cas où aucune information n’est échangée entre les utilisateurs secondaires (pour éviter les surcoûts en transmissions). Ce problème particulier est modélisé par une approche dite de bandits manchots « restless » markoviens multi-utilisateurs (multi-user restless Markov MAB -multi¬armed bandit). La contribution principale de cette thèse propose une stratégie d’apprentissage multi-joueurs qui prend en compte non seulement le critère de disponibilité des canaux (comme déjà étudié dans la littérature et une thèse précédente au laboratoire), mais aussi une métrique de qualité, comme par exemple le niveau d’interférence mesuré (sensing) dans un canal (perturbations issues des canaux adjacents ou de signaux distants). Nous prouvons que notre stratégie, RQoS-UCB distribuée (distributed restless QoS-UCB – Upper Confidence Bound), est quasi optimale car on obtient des performances au moins d’ordre logarithmique sur son regret. En outre, nous montrons par des simulations que les performances du système intelligent proposé sont améliorées significativement par l’utilisation de la solution d’apprentissage proposée permettant à l’utilisateur secondaire d’identifier plus efficacement les ressources fréquentielles les plus disponibles et de meilleure qualité. Cette thèse propose également un nouveau modèle d’apprentissage par renforcement combiné à un transfert de connaissance afin d’améliorer l’efficacité énergétique (EE) des réseaux cellulaires hétérogènes. Nous formulons et résolvons un problème de maximisation de l’EE pour le cas de stations de base (BS – Base Stations) dynamiquement éteintes et allumées (ON-OFF). Ce problème d’optimisation combinatoire peut aussi être modélisé par des bandits manchots « restless » markoviens. Par ailleurs, une gestion dynamique de la topologie des réseaux hétérogènes, utilisant l’algorithme RQoS-UCB, est proposée pour contrôler intelligemment le mode de fonctionnement ON-OFF des BS, dans un contexte de trafic et d’étude de capacité multi-cellulaires. Enfin une méthode incluant le transfert de connaissance « transfer RQoS-UCB » est proposée et validée par des simulations, pour pallier les pertes de récompense initiales et accélérer le processus d’apprentissage, grâce à la connaissance acquise à d’autres périodes temporelles correspondantes à la période courante (même heure de la journée la veille, ou même jour de la semaine par exemple). La solution proposée de gestion dynamique du mode ON-OFF des BS permet de diminuer le nombre de BS actives tout en garantissant une QoS adéquate en atténuant les fluctuations de la QoS lors des variations du trafic et en améliorant les conditions au démarrage de l’apprentissage. Ainsi, l’efficacité énergétique est grandement améliorée. Enfin des démonstrateurs en conditions radio réelles ont été développés pour valider les solutions d’apprentissage étudiées. Les algorithmes ont également été confrontés à des bases de données de mesures effectuées par un partenaire dans la gamme de fréquence HF, pour des liaisons transhorizon. Les résultats confirment la pertinence des solutions d’apprentissage proposées, aussi bien en termes d’optimisation de l’utilisation du spectre fréquentiel, qu’en termes d’efficacité énergétique. / Future cellular network technologies are targeted at delivering self-organizable and ultra-high capacity networks, while reducing their energy consumption. This thesis studies intelligent spectrum and topology management through cognitive radio techniques to improve the capacity density and Quality of Service (QoS) as well as to reduce the cooperation overhead and energy consumption. This thesis investigates how reinforcement learning can be used to improve the performance of a cognitive radio system. In this dissertation, we deal with the problem of opportunistic spectrum access in infrastructureless cognitive networks. We assume that there is no information exchange between users, and they have no knowledge of channel statistics and other user's actions. This particular problem is designed as multi-user restless Markov multi-armed bandit framework, in which multiple users collect a priori unknown reward by selecting a channel. The main contribution of the dissertation is to propose a learning policy for distributed users, that takes into account not only the availability criterion of a band but also a quality metric linked to the interference power from the neighboring cells experienced on the sensed band. We also prove that the policy, named distributed restless QoS-UCB (RQoS-UCB), achieves at most logarithmic order regret. Moreover, numerical studies show that the performance of the cognitive radio system can be significantly enhanced by utilizing proposed learning policies since the cognitive devices are able to identify the appropriate resources more efficiently. This dissertation also introduces a reinforcement learning and transfer learning frameworks to improve the energy efficiency (EE) of the heterogeneous cellular network. Specifically, we formulate and solve an energy efficiency maximization problem pertaining to dynamic base stations (BS) switching operation, which is identified as a combinatorial learning problem, with restless Markov multi-armed bandit framework. Furthermore, a dynamic topology management using the previously defined algorithm, RQoS-UCB, is introduced to intelligently control the working modes of BSs, based on traffic load and capacity in multiple cells. Moreover, to cope with initial reward loss and to speed up the learning process, a transfer RQoS-UCB policy, which benefits from the transferred knowledge observed in historical periods, is proposed and provably converges. Then, proposed dynamic BS switching operation is demonstrated to reduce the number of activated BSs while maintaining an adequate QoS. Extensive numerical simulations demonstrate that the transfer learning significantly reduces the QoS fluctuation during traffic variation, and it also contributes to a performance jump-start and presents significant EE improvement under various practical traffic load profiles. Finally, a proof-of-concept is developed to verify the performance of proposed learning policies on a real radio environment and real measurement database of HF band. Results show that proposed multi-armed bandit learning policies using dual criterion (e.g. availability and quality) optimization for opportunistic spectrum access is not only superior in terms of spectrum utilization but also energy efficient.