 IDEALS Home
 →
 College of Engineering
 →
 Browse College of Engineering by Contributor
Browse College of Engineering by Contributor "Raginsky, Maxim"
Now showing items 120 of 25

(20140530)The thesis addresses a problem in networked control systems where quantization is a communication constraint. Control design together with parameter estimation algorithms lead to adaptive control techniques. A first order ...
application/pdf
PDF (420kB) 
(20181203)Blind linear system identification (or recovery) arises in several applications in engineering (e.g. channel equalization, superresolution, MRI and SAR image formation). This is a special case of a bilinear inverse ...
application/pdf
PDF (10MB) 
(201805)This thesis analyzes the Bayesian control law for adaptive control proposed by Ortega and Braun. The problem of concern is as follows: Assume the agent is put into an unknown environment that is sampled from certain ...
application/pdf
PDF (260kB) 
(20151204)Artificial Intelligence (AI) has been a source of great intrigue and has spawned many questions regarding the human condition and the core of what it means to be a sentient entity. The field has bifurcated into socalled ...
application/pdf
PDF (13MB) 
(20150121)This thesis introduces a framework of channel emulation. An emulator is defined as a pair of channels, that converts one channel to another channel with possibly different input and output alphabets. With the concept of ...
application/pdf
PDF (338kB) 
(20190712)This thesis is concerned with the design and analysis of particlebased algorithms for two problems: (i) the nonlinear filtering problem; (ii) and the problem of sampling from a target distribution. The contributions for ...
application/pdf
PDF (1MB) 
(20140916)The thesis focuses on a few fundamental problems in multiplayer dynamic sequential decision problems  games and teams  with asymmetric information. It is divided into two parts and addresses six broad theoretical ...
application/pdf
PDF (2MB) 
(20180709)A distributed system is composed of independent agents, machines, processing units, etc., where interactions between them are usually constrained by a network structure. In contrast to centralized approaches where all ...
application/pdf
PDF (5MB) 
(20120918)How does uncertainty affect a robot when attempting to generate a control policy to achieve some objective? How sensitive is the obtained control policy to perturbations? These are the central questions addressed in this ...
application/pdf
PDF (2MB) 
(20150121)This thesis focuses on designing efficient mechanisms for controlling information spread in networks. We consider two models for information spread. The first one is the wellknown distributed averaging dynamics. The second ...
application/pdf
PDF (8MB) 
(20190819)As the era of big data arises, people get access to numerous amounts of multiview data. Measuring, discovering and understanding the underlying relationship among different aspects of data is the core problem in information ...
application/pdf
PDF (4MB) 
(20190814)The focus of this thesis is on understanding machine learning algorithms from an informationtheoretic point of view. More specifically, we apply informationtheoretic tools to construct performance bounds for the learning ...
application/pdf
PDF (1MB) 
(20161130)In a generic distributed information processing system, a number of agents connected by communication channels aim to accomplish a task collectively through local communications. The fundamental limits of distributed ...
application/pdf
PDF (2MB) 
(20140530)Nextgeneration embedded devices are expected to pervasively extract information from the world around us. In particular, growing interest in mobile devices beyond the smart phone imply that the need for context awareness ...
application/pdf
PDF (3MB) 
(20150421)Algorithms on graphs are used extensively in many applications and research areas. Such applications include machine learning, artificial intelligence, communications, image processing, state tracking, sensor networks, ...
application/pdf
PDF (5MB) 
(20151204)This thesis studies MMSE estimation on the basis of quantized noisy observations. It presents nonasymptotic bounds on MMSE regret due to quantization for two settings: (1) estimation of a scalar random variable given a ...
application/pdf
PDF (320kB) 
(20190128)In this dissertation, a circuit modeling methodology using recurrent neural networks (RNNs) is developed. The methodology covers model structure selection, data generation, training, and model implementation for circuit ...
application/pdf
PDF (3MB) 
(20150518)We propose a novel group testing framework, termed semiquantitative group testing, motivated by a class of problems arising in genome screening experiments in addition to other applications such as interpretable rule ...
application/pdf
PDF (1MB) 
(20180904)Recent advances in genetics, computer vision, and text mining are accompanied by analyzing data coming from a large domain, where the domain size is comparable or larger than the number of samples. In this dissertation, ...
application/pdf
PDF (2MB) 
(20150121)This thesis poses a general model for optimal control subject to information constraint, motivated in part by recent work on informationconstrained decisionmaking by economic agents. In the averagecost optimal control ...
application/pdf
PDF (454kB)
Now showing items 120 of 25