No description available.

No description available.

No description available.

In modern data science, it is common that large-scale data are stored and processed parallelly across a great number of locations. For reasons including confidentiality concerns, only limited data information from each parallel center is eligible to be transferred. To solve these problems more efficiently, a group of communication-efficient methods are being actively developed. The first part of our investigation is the distributions of the distributed M-estimators that require a one-step update, combining data information collected from all parallel centers. We reveal that the number of centers plays a critical role. When it is not small compared with the total sample size, a non-negligible impact occurs to the limiting distributions, which turn out to be mixtures involving products of normal random variables. Based on our analysis, we propose a multiplier-bootstrap method for approximating the distributions of these one-step updated estimators. Our second contribution is that we propose two communication-efficient Newton-type algorithms, combining the M-estimator and the gradient collected from each data center. They are created by constructing two Fisher information estimators globally with those communication-efficient statistics. Enjoying a higher rate of convergence, this framework improves upon existing Newton-like methods. Moreover, we present two bias-adjusted one-step distributed estimators. When the square of the center-wise sample size is of a greater magnitude than the total number of centers, they are as efficient as the global M-estimator asymptotically. The advantages of our methods are illustrated by extensive theoretical and empirical evidences. / Statistics

An influence diagram is a widely-used graphical model for representing and solving problems of sequential decision making under imperfect information. A closely-related model for the same class of problems is a partially observable Markov decision process (POMDP). This dissertation leverages the relationship between these two models to develop improved algorithms for solving influence diagrams. The primary contribution is to generalize two classic dynamic programming algorithms for solving influence diagrams, Arc Reversal and Variable Elimination, by integrating them with a dynamic programming technique originally developed for solving POMDPs. This generalization relaxes constraints on the ordering of the steps of these algorithms in a way that dramatically improves scalability, especially in solving complex, multi-stage decision problems. A secondary contribution is the adoption of a more compact and intuitive representation of the solution of an influence diagram, called a strategy. Instead of representing a strategy as a table or as a tree, a strategy is represented as an acyclic graph, which can be exponentially more compact, making the strategy easier to interpret and understand.

No description available.

RNA (Ribonuceic Acid) sequencing technology is a powerful technology used to give re- searchers essential information about the functionality of genes. The transcriptomic study and downstream analysis highlight the functioning of the genes associated with a specific biological process/treatment. In practice, differentially expressed genes associated with a particular treatment or genotype are subjected to downstream analysis to find some critical set of genes. This critical set of genes/ genes pathways infers the effect of the treatment in a cell or tissue. This disserta- tion describes the multiple stages framework of finding these critical sets of genes using different analysis methodologies and inference algorithms. RNA sequencing technology helps to find the differentially expressed genes associated with the treatments and genotypes. The preliminary step of RNA-seq analysis consists of extracting the mRNA(messenger RNA) followed by mRNA libraries’ preparation and sequencing using the Illumina HiSeq 2000 platform. The later stage analysis starts with mapping the RNA sequencing data (obtained from the previous step) to the genome annotations and counting each annotated gene’s reads to produce the gene expression data. The second step involves using the statistical method such as linear model fit, clustering, and probabilistic graphical modeling to analyze genes and gene networks’ role in treatment responses. In this dissertation, an R software package is developed that compiles all the RNA sequencing steps and the downstream analysis using the R software and Linux environment. Inference methodology based on loopy belief propagation is conducted on the gene networks to infer the differential expression of the gene in the further step. The loopy belief propagation algorithm uses a computational modeling framework that takes the gene expression data and the transcriptional Factor interacting with the genes. The inference method starts with constructing a gene-Transcriptional Factor network. The construction of the network uses an undirected proba- bilistic graphical modeling approach. Later the belief message is propagated across all the nodes of the graphs. The analysis and inference methods explained in the dissertation were applied to the Arabidopsis plant with two different genotypes subjected to two different stress treatments. The results for the analysis and inference methods are reported in the dissertation.

Recent research shows that machine learning algorithms are highly susceptible to attacks trying to extract sensitive information about the data used in model training. These attacks called privacy attacks, exploit the model training process. Contemporary defense techniques make alterations to the training algorithm. Such defenses are computationally expensive, cause a noticeable privacy-utility tradeoff, and require control over the training process. This thesis presents a data-centric approach using data augmentations to mitigate privacy attacks. We present privacy-focused data augmentations to change the sensitive data submitted to the model trainer. Compared to traditional defenses, our method provides more control to the individual data owner to protect one's private data. The defense is model-agnostic and does not require the data owner to have any sort of control over the model training. Privacypreserving augmentations are implemented for two attacks namely membership inference and model inversion using two distinct techniques. While the proposed augmentations offer a better privacy-utility tradeoff on CIFAR-10 for membership inference, they reduce the reconstruction rate to ≤ 1% while reducing the classification accuracy by only 2% against model inversion attacks. This is the first attempt to defend model inversion and membership inference attacks using decentralized privacy protection. / Master of Science / Privacy attacks are threats posed to extract sensitive information about the data used to train machine learning models. As machine learning is used extensively for many applications, they have access to private information like financial records, medical history, etc depending on the application. It has been observed that machine learning models can leak the information they contain. As models tend to 'memorize' training data to some extent, even removing the data from the training set cannot prevent privacy leakage. As a result, the research community has focused its attention on developing defense techniques to prevent this information leakage. However, the existing defenses rely heavily on making alterations to the way a machine learning model is trained. This approach is termed as a model-centric approach wherein the model owner is responsible to make changes to the model algorithm to preserve data privacy. By doing this, the model performance is degraded while upholding data privacy. Our work introduces the first data-centric defense which provides the tools to protect the data to the data owner. We demonstrate the effectiveness of the proposed defense in providing protection while ensuring that the model performance is maintained to a great extent.

No description available.

京都大学 / 新制・課程博士 / 博士(情報学) / 甲第24727号 / 情博第815号 / 新制||情||137(附属図書館) / 京都大学大学院情報学研究科知能情報学専攻 / (主査)教授 鹿島 久嗣, 教授 阿久津 達也, 教授 下平 英寿 / 学位規則第4条第1項該当 / Doctor of Informatics / Kyoto University / DFAM