Spelling suggestions: "subject:"[een] DISTRIBUTED LEARNING"" "subject:"[enn] DISTRIBUTED LEARNING""
31 |
Distributed Algorithms for Power Allocation Games on Gaussian Interference ChannelsKrishnachaitanya, A January 2016 (has links) (PDF)
We consider a wireless communication system in which there are N transmitter-receiver pairs and each transmitter wants to communicate with its corresponding receiver. This is modelled as an interference channel. We propose power allocation algorithms for increasing the sum rate of two and three user interference channels. The channels experience fast fading and there is an average power constraint on each transmitter. In this case receivers use successive decoding under strong interference, instead of treating interference as noise all the time. Next, we u se game theoretic approach for power allocation where each receiver treats interference as noise. Each transmitter-receiver pair aims to maximize its long-term average transmission rate subject to an average power constraint. We formulate a stochastic game for this system in three different scenarios. First, we assume that each user knows all direct and crosslink channel gains.
Next, we assume that each user knows channel gains of only the links that are incident on its receiver. Finally, we assume that each use r knows only its own direct link channel gain. In all cases, we formulate the problem of finding the Nash equilibrium(NE) as a variational in equality problem. For the game with complete channel knowledge, we present an algorithm to solve the VI and we provide weaker sufficient conditions for uniqueness of the NE than the sufficient conditions available in the literature. Later, we present a novel heuristic for solving the VI under general channel conditions. We also provide a distributed algorithm to compute Pare to optimal solutions for the proposed games. We use Bayesian learning that guarantees convergence to an Ɛ-Nash equilibrium for the incomplete information game with direct link channel gain knowledge only, that does not require knowledge of the power policies of other users but requires feedback of the interference power values from a receiver to its corresponding transmitter.
Later, we consider a more practical scenario in which each transmitter transmits data at a certain rate using a power that depends on the channel gain to its receiver. If a receiver can successfully receive the message, it sends an acknowledgement(ACK), else it sends a negative ACK(NACK). Each user aims to maximize its probability of successful transmission. We formulate this problem as a stochastic game and propose a fully distributed learning algorithm to find a correlated equilibrium(CE). In addition, we use a no regret algorithm to find a coarse correlated equilibrium(CCE) for our power allocation game. We also propose a fully distributed learning algorithm to find a Pareto optimal solution. In general Pareto points do not guarantee fairness among the users. Therefore we also propose an algorithm to compute a Nash bargaining solution which is Pareto optimal and provides fairness among the users. Finally, we extend these results when each transmitter sends data at multiple rates rather than at a fixed rate.
|
32 |
New Approaches Towards Online, Distributed, and Robust Learning of Statistical Properties of DataTong Yao (16644750) 07 August 2023 (has links)
<p>In this thesis, we present algorithms to allow agents to estimate certain properties in a robust, online, and distributed manner. Each agent receives a sequence of observations, and through communication, collectively infers properties of the data gathered by all agents by communicating.</p>
<p><br></p>
<p>In the first part of the thesis, we provide algorithms to infer the correlations between interacting entities from these large datasets. Gaussian graphical models have been well studied to represent the relationships between the various random variables which generate data, and numerous algorithms have been proposed to learn the dependencies in such models. However, existing algorithms typically process data in a batch at a central location, limiting their applications in scenarios where data arrive in real-time and are gathered by different agents. </p>
<p><br></p>
<p>To address these challenges, first, we propose an online sparse inverse covariance algorithm to infer the static network structure (i.e., dependencies between nodes) in real-time from time-series data, in a centralized location. Subsequently, we propose a distributed algorithm to cooperatively learn the network structure in real-time from data collected by distributed agents. We characterize the theoretical convergence properties and provide simulations using synthetic datasets and real-world hurricane Twitter datasets in disaster management applications. </p>
<p><br></p>
<p>The second part of this thesis addresses the robustness of online and distributed learning under arbitrary data corruption. We propose online and distributed algorithms for robust mean, covariance, and sparse inverse covariance estimation. These algorithms are capable of operating effectively even in the presence of adversarial data attacks. We provide theoretical bounds on the error and rate of convergence of these methods and evaluate their performance under various settings.</p>
<p><br></p>
<p>Finally, we consider the problem of classification with a network of heterogeneous and partially informative agents, each receiving local data from an underlying true class, and equipped with a classifier that only distinguishes between a subset of the entire set of classes. We propose an iterative algorithm that uses the posterior probabilities of any classifier and recursively updates each agent's local belief based on its local signals and belief information from its neighbors. We then adopt a novel distributed min-rule to update each agent’s global belief and enable learning of the true class for all agents. We analyze the convergence properties of our proposed algorithm, and subsequently, demonstrate and compare its performance with local averaging and global average consensus through simulations and with a visual image dataset.</p>
|
33 |
Learning optimizers for communication-efficient distributed learningJoseph, Charles-Étienne 07 1900 (has links)
Ce mémoire propose d'utiliser des optimiseurs appris, soit une approche tirée du méta-apprentissage, pour améliorer l'optimisation distribuée. Nous présentons deux architectures d'optimiseurs appris et nous montrons qu'elles sont plus performantes que les référentiels de l'état de l'art tout en généralisant aux ensembles de données et aux architectures inconnues. Nous établissons ainsi l'optimisation apprise comme une direction prometteuse pour l'apprentissage distribué efficace en termes de communication. Nous explorons également l'application des optimiseurs appris à l'apprentissage fédéré, une technique visant à la vie privée où les données restent sur les appareils individuels. Nos résultats démontrent que les optimiseurs appris obtiennent de bonnes performances dans des contextes d'apprentissage fédéré, entre autres avec une distribution hétérogène des données entre les clients. Enfin, ce mémoire étudie la combinaison des optimiseurs appris avec la parcimonification des gradients, une technique qui réduit la communication en ne transmettant qu'un sous-ensemble de gradients. Nos résultats montrent que les optimiseurs appris peuvent effectivement tirer parti de la parcimonie pour améliorer l'efficacité de la communication. Dans l'ensemble, ce mémoire démontre l'efficacité des optimiseurs appris pour l'apprentissage distribué efficace en termes de communication. Nous ouvrons également la voie à une exploration plus poussée de la combinaison des optimiseurs appris avec d'autres techniques visant l'efficacité en termes de communication. / This thesis proposes the use of learned optimizers, a meta-learning approach, to improve distributed optimization. We present two learned optimizer architectures and show that they outperform state-of-the-art baselines while generalizing to unknown datasets and architectures. We thus establish learned optimization as a promising direction for communication-efficient distributed learning. We also explore the application of learned optimizers to federated learning, a privacy-oriented setting where data remains on individual devices. Our results show that learned optimizers perform well in federated learning contexts, including for setups with heterogeneous data distribution among clients. Finally, this thesis investigates the combination of learned optimizers with gradient sparsification, a technique that reduces communication by transmitting only a subset of gradients. Our results show that learned optimizers can indeed take advantage of sparsification to improve communication efficiency. Overall, this thesis demonstrates the effectiveness of learned optimizers for communication-efficient distributed learning. We also pave the way for further exploration of learned optimizers combined with other techniques targeting communication efficiency.
|
34 |
New media and self-directed learning : enhancing pedagogical transformation in an open distance learning landscapeMbatha, B. (Blessing) 02 1900 (has links)
Modern technological innovations are constantly seen throughout every aspect of life, and higher education is no exception. To this end, this article sheds some light on the types of and pedagogical value of new media adopted by academics to promote self-directed learning at the University of South Africa. The study answers the following questions: Which new media approaches have been adopted by academics to enhance self-directed learning? What is the pedagogical value of new media in an ODL environment? A qualitative approach was employed and data was collected through face-to-face interviews with 30 purposively selected Unisa academics. The Unified Theory of Acceptance and Use of Technology model was found relevant to this study. Thematic categorisation was employed for data analysis. The findings depict that a variety of new media have been adopted to promote self-directed learning at Unisa. The study also found that new media are playing a pivotal role in promoting self-directed learning in an ODL landscape. It is therefore important to note that new media have emerged as strong catalysts in fostering pedagogical transformation. / College of Education / M. Ed (Open and Distance Learning)
|
35 |
Increasing motivation by adapting intelligent tutoring instruction to learner achievement goalsLockhart, Tony F. 05 April 2011 (has links)
The impact of affect on learning and performance has caused many researchers in the field of cognitive psychology to acknowledge the value of motivationally supportive instruction. Goal orientation, which refers to the perceptions and behaviors of the learner in achievement situations, has been the most predominant theory in learning motivation. However, research suggests multiple components are responsible for affecting student cognitive engagement. The traditional framework distinguishes individuals who are self-motivated to master challenging tasks from those who are motivated to earn favorable judgments of performance as intrinsic and extrinsic learners, respectively. In addition, learners may be further categorized by an eagerness to ensure a positive outcome or by their vigilance in avoiding negative outcomes. As such, my research explores how these motivational categories can be utilized to construct a more robust instructional model.
The objective of this research is to evaluate the effectiveness of adaptive remediation strategies on motivation and learning performance. Research suggests the cost of integrating cognitive tasks with error analysis outweigh the benefits of sparse learning gains. However, further investigation is required to understand how feedback can improve these outcomes. The experiment presented here seeks to evaluate the adaptive instruction of two pedagogical agents embedded within two separate versions of the Virtual BNI Trainer. The basic coach uses a model of the learner's experience level to determine an appropriate level of elaboration required during remediation. In contrast, the motivationally enhanced coach uses a model of the learner's goal orientation to construct feedback that appeals to their natural disposition.
A controlled experiment was conducted to evaluate the effects of adaptive instruction on student self-efficacy, engagement, and learning performance in the Virtual BNI Training Environment. The results of this experiment are used to establish guidelines for integrating goal orientation, error analysis, and feedback within a virtual coach, to improve motivation and learning performance. In addition, these findings also indicate areas for future research.
|
36 |
[en] SIGNAL PROCESSING TECHNIQUES FOR ENERGY EFFICIENT DISTRIBUTED LEARNING / [pt] TÉCNICAS DE PROCESSAMENTO DE SINAIS PARA APRENDIZAGEM DISTRIBUÍDA COM EFICIÊNCIA ENERGÉTICAALIREZA DANAEE 11 January 2023 (has links)
[pt] As redes da Internet das Coisas (IdC) incluem dispositivos inteligentes que contêm muitos sensores que permitem interagir com o mundo físico, coletando e processando dados de streaming em tempo real. O consumo total de energia e o custo desses sensores afetam o consumo de energia
e o custo dos dispositivos IdC. O tipo de sensor determina a precisão da
interface analógica e a resolução dos conversores analógico-digital (ADCs). A
resolução dos ADCs tem um compromisso entre a precisão de inferência e o
consumo de energia, uma vez que o consumo de energia dos ADCs depende
do número de bits usados para representar amostras digitais.
Nesta tese, apresentamos um esquema de aprendizado distribuído com eficiência
energética usando sinais quantizados para redes da IdC. Em particular,
desenvolvemos algoritmos de gradiente estocástico com reconhecimento de
quantização distribuído (DQA-LMS) e de mínimos quadrados recursivos com
reconhecimento de quantização distribuído (DQA-RLS) que podem aprender
parâmetros de maneira eficiente em energia usando sinais quantizados com
poucos bits, exigindo um baixo custo computacional. Além disso, desenvolvemos
uma estratégia de compensação de viés para melhorar ainda mais o
desempenho dos algoritmos propostos. Uma análise estatística dos algoritmos
propostos juntamente com uma avaliação da complexidade computacional
das técnicas propostas e existentes é realizada. Os resultados numéricos
avaliam os algoritmos com reconhecimento de quantização distribuída em
relação às técnicas existentes para uma tarefa de estimação de parâmetros
em que os dispositivos IdC operam em um modo ponto a ponto.
Também apresentamos um esquema de aprendizado federativo com eficiência
energética usando sinais quantizados para redes de IdC. Desenvolvemos o
algoritmo federated averaging LMS (QA-FedAvg-LMS) com reconhecimento
de quantização para redes IdC estruturadas por configuração de aprendizado
federativo em que os dispositivos IdC trocam suas estimativas com um
servidor. Uma estratégia de compensação de viés para QA-FedAvg-LMS é
proposta junto com sua análise estatística e a avaliação de desempenho em
relação às técnicas existentes com resultados numéricos. / [en] Internet of Things (IoT) networks include smart devices that contain many sensors that allow them to interact with the physical world, collecting and processing streaming data in real time. The total energy-consumption and cost of these sensors affect the energy-consumption and the cost of IoT
devices. The type of sensor determines the accuracy of the analog interface and the resolution of the analog-to-digital converters (ADCs). The ADC resolution requirement has a trade-off between sensing performance and energy consumption since the energy consumption of ADCs strongly depends
on the number of bits used to represent digital samples. In this thesis, we present an energy-efficient distributed learning framework using coarsely quantized signals for IoT networks. In particular, we develop
a distributed quantization-aware least-mean square (DQA-LMS) and a distributed quantization-aware recursive least-squares (DQA-RLS) algorithms that can learn parameters in an energy-efficient fashion using signals quantized with few bits while requiring a low computational cost. Moreover, we
develop a bias compensation strategy to further improve the performance of the proposed algorithms. We then carry out a statistical analysis of the proposed algorithms along with a computational complexity evaluation of the proposed and existing techniques. Numerical results assess the distributed
quantization-aware algorithms against existing techniques for distributed parameter estimation where IoT devices operate in a peer-to-peer mode. We also introduce an energy-efficient federated learning framework using coarsely quantized signals for IoT networks, where IoT devices exchange
their estimates with a server. We then develop the quantization-aware federated averaging LMS (QA-FedAvg-LMS) algorithm to perform parameter estimation at the clients and servers. Furthermore, we devise a bias compensation strategy for QA-FedAvg-LMS, carry out its statistical analysis,
and assess its performance against existing techniques with numerical results.
|
37 |
ICTS: A catalyst for enriching the learning process and library services in IndiaChandra, Smita, Patkar, Vivek January 2007 (has links)
The advances in ICTs have decisively changed the library and learning environment. On the one hand, ICTs have enhanced the variety and accessibility to library collections and services to break the barriers of location and time. On the other, the e-Learning has emerged as an additional medium for imparting education in many disciplines to overcome the constraint of physical capacity associated with the traditional classroom methods. For a vast developing country like India, this provides an immense opportunity to provide even higher education to remote places besides extending the library services through networking. Thanks to the recent initiatives by the public and private institutions in this direction, a few web-based instruction courses are now running in the country. This paper reviews different aspects of e-Learning and emerging learning landscapes. It further presents the
library scene and new opportunities for its participation in the e-Learning process. How these ICTs driven advances can contribute to the comprehensive learning process in India is highlighted.
|
38 |
e-Research and the Ubiquitious Open Grid Digital Libraries of the FuturePatkar, Vivek, Chandra, Smita January 2006 (has links)
Libraries have traditionally facilitated each of the following elements of research: production of new knowledge, its preservation and its organization to make it accessible for use over the generations. In modern times, the library is constantly required to meet the challenges of information explosion. Assimilating resources and restructuring practices to process the large data volumes both in the print and digital form held across the globe, therefore, becomes very important. A recourse by the libraries to application of successive forms of what can be called as Digital Library Technologies (DLT) has been the imperative. The Open Archives Initiative (OAI) is one recent development that is expected to assist the libraries to partner in setting up virtual learning environment and integrating research on a near universal scale. Future extension of this concept is envisaged to be that of Grid Computing. The technologies driving the â Gridâ would let people share computing power, databases, and other on-line tools securely across institutional and geographic boundaries without sacrificing the local autonomy. Ushering an era of the ubiquitous library helping the e-research is thus on the card. This paper reviews the emerging technological changes and charts the future role for the libraries with special reference to India.
|
Page generated in 0.24 seconds