2026-09-18T21:55:39Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/978092026-06-17T14:46:25Zcom_1721.1_7582com_1721.1_7581col_1721.1_131022

Tomaso Poggio and Lorenzo Rosasco. Mroueh, Youssef Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2015-07-17T19:48:53Z 2015-07-17T19:48:53Z 2015 2015 http://hdl.handle.net/1721.1/97809 912309122 Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2015. Cataloged from PDF version of thesis. Includes bibliographical references (pages 174-182). A quantization approach to supervised learning, compressive sensing, and phase retrieval is presented in this thesis. We introduce a set of common techniques that allow us, in those three settings, to represent high dimensional data using the order statistics of linear and non linear measurements. We introduce new algorithms for signals classification in the multiclass and the multimodal settings, as well as algorithms for signals representation and recovery from quantized linear and quadratic measurements. We analyze the statistical consistency of our algorithms and prove their robustness to different sources of perturbation, as well as their computational efficiency. We present and analyze applications of our theoretical results in realistic setups, such as computer vision classification tasks, Audio-Visual Automatic Speech Recognition, lossy image compression and retrieval via locality sensitive hashing, locally linear estimation in large scale learning and Fourier sampling for phase retrieval - of particular interest in X-ray crystallography and super-resolution diffraction imaging applications. Our analysis of quantization based algorithms highlights interesting tradeoffs between memory complexity, sample complexity, and time complexity in algorithms design. by Youssef Mroueh. Ph.D. 182 pages eng Massachusetts Institute of Technology M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission. http://dspace.mit.edu/handle/1721.1/7582 Electrical Engineering and Computer Science. From bits to information : learning meets compressive sensing Thesis application/pdf Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="bed15efa-5e70-40ae-ae3c-b6763ec2cd83"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Language>eng</Language> <Title>From bits to information : learning meets compressive sensing</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2015</PublicationDate> <Authors> <Author> <DisplayName>Mroueh, Youssef</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Massachusetts Institute of Technology</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>http://dspace.mit.edu/handle/1721.1/7582</License> <Keyword>Electrical Engineering and Computer Science.</Keyword> <Abstract>A quantization approach to supervised learning, compressive sensing, and phase retrieval is presented in this thesis. We introduce a set of common techniques that allow us, in those three settings, to represent high dimensional data using the order statistics of linear and non linear measurements. We introduce new algorithms for signals classification in the multiclass and the multimodal settings, as well as algorithms for signals representation and recovery from quantized linear and quadratic measurements. We analyze the statistical consistency of our algorithms and prove their robustness to different sources of perturbation, as well as their computational efficiency. We present and analyze applications of our theoretical results in realistic setups, such as computer vision classification tasks, Audio-Visual Automatic Speech Recognition, lossy image compression and retrieval via locality sensitive hashing, locally linear estimation in large scale learning and Fourier sampling for phase retrieval - of particular interest in X-ray crystallography and super-resolution diffraction imaging applications. Our analysis of quantization based algorithms highlights interesting tradeoffs between memory complexity, sample complexity, and time complexity in algorithms design.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>