Browsing by Subject "Recovery"

Now showing 1 - 6 of 6
  • Thumbnail Image
    Item
    Data Permutation Recovery from Noisy Data: Error Probability and Privacy
    (2024-05) Jeong, Minoh
    This doctoral thesis investigates the data permutation recovery problem from noisy observations, a fundamental challenge at the intersection of data science and privacy-preserving technologies. The main question is: Given a noisy observation of data, according to which permutation was the original data sorted? This thesis addresses both the exact and approximate permutation recovery problems under various noise conditions. It begins by formulating the permutation recovery problem within the statistical hypothesis testing framework, and characterizes the linear regime, where the true permutation can be optimally estimated by only a linear transformation of the observation and a sorting operation. In particular, under Gaussian data and noise, this thesis derives the necessary and sufficient conditions for the linear regime in terms of the noise covariance matrix. Subsequently, this thesis shifts the focus to the examination of the error probability associated with linear decoders in the presence of Gaussian noise, but arbitrary data distribution. This analysis reveals the noise-dominated nature of the permutation recovery problem, illustrating how the error probability scales in both low- and high-noise regimes, and providing insights into the behavior of the error probability under different noise and data distributions. Specifically, the error probability of the permutation recovery problem grows linearly in the noise standard deviation σ in the low-noise regime, implying the noise-dominated nature of the problem. Advancing into the realm of data privacy, the thesis explores the private rank- ing recovery problem, aiming to establish fundamental trade-offs between estimation accuracy and privacy. Leveraging differential privacy metrics, it evaluates the effectiveness of various privacy-preserving mechanisms while ensuring the fidelity of the ranking recovery. Regarding the generalized permutation recovery problem, this thesis also proposes an approximate version of it. It demonstrates that this approximate version leads to an error probability having sub-linear behavior in σ in the low-noise regime, which is a notable difference with respect to the exact recovery. This finding highlights the potential of approximate recovery in enhancing the robustness and efficiency of permutation recovery. In summary, the thesis contributes significantly to our understanding of permutation recovery in noisy and privacy-sensitive environments. The thesis not only advances theoretical foundations but also provides practical strategies for tackling the challenges inherent in recovering data permutations, thereby offering valuable perspectives for advancements in data processing and privacy-preserving techniques.
  • Thumbnail Image
    Item
    Essays on macroeconomics
    (2013-07) Guo, Si
    The dissertation includes two essays. In the first essay I try to explain the slow recovery of the U.S. economy after the 2008-2009 recession. I develop a theory in which the slow recovery is due to continuing weak consumption demand arising from slowly resolved aggregate uncertainty. An exogenous belief shock creates uncertainty about firms' credit availability. This translates into income uncertainty at the household level because firms have to borrow from banks in order to hire workers. In response, household demand is low, which in turn causes firms to borrow little and produce little. This low level of economic activity impedes the resolution of uncertainty regarding credit availability. Therefore, the economy stagnates with high uncertainty, low demand, and low output, even though there is no shock to fundamentals. The resolution of uncertainty is not efficient because households do not fully internalize the effect of increasing their own demand on improving the quality of information. This leaves room for government intervention. Quantitatively my model generates a slow recovery, which is comparable to U.S. employment data. Model pre- dictions are also consistent with U.S. county level data: counties with cheaper access to household credit have higher employment but all counties recover at the same rate. In the second essay, which is co-authored with Yun Pei, we try to understand the impact of sovereign default on the lending countries. We develop a model in which banks in the lending countries can buy foreign sovereign bond, provide loan to domestic firms and borrow from domestic households. We find that a sovereign default in foreign countries can result in an output drop in the lending countries, because the default can worsen the balance sheet of banks. Therefore default risk in foreign countries can be transmitted to output risk in the lending countries. However, this does not mean that the governments in the lending countries should limit the purchase of foreign sovereign bond. A tax on the purchase of sovereign bond reduces the output fluctuation but also decreases the welfare of domestic bankers and households.
  • Thumbnail Image
    Item
    From tragedy to opportunity: long-term development in post-disaster intentional communities in Honduras.
    (2012-06) Alaniz, Ryan Chelese
    With 2010 witnessing the second highest number of global disasters in history, climate change has spurred interest concerning how non-governmental organizations (NGOs) should respond with long-term development strategies in post-disaster communities, especially those in fragile states. This comparative case study examines how two intentional Honduran communities built for survivors (comprised of traumatized and displaced poor people) of Hurricane Mitch (1998), Divina Providencia and Ciudad España, developed since the disaster. Although initially similar based on demographics, the communities are dramatically different today in social health (defined as low crime, social capital, social cohesion, vision, sustainability, and community participation). My doctoral research combines household surveys (N=1,918), 74 interviews, nine months of ethnography, and archival research in an analysis of what mechanisms shaped the social health trajectory of each community. I found that both communities have had varying degrees of success and conflict due in large part to the Honduran context and decisions and practices implemented by sponsoring non-governmental organization including: time horizons/long-term commitment, organizational resources, spatial design, community size, and coercive mechanisms by the organizations. Although both communities faced similar constraints, such as trauma and broken social networks, Divina overcame many hurdles with the help of a strong NGO presence, organizational resources, a long-term commitment, and coercive means. It was able to foster cultural structures that created a healthier community than resident pre-Mitch neighborhoods in Tegucigalpa. Certain emergent norms of community life prevented the Divina community from falling back upon old structures and norms (which were inequitable and socially unhealthy). However, its top-down paternalist approach led to protests by community residents, the creation of dependency on the NGO, and issues of possible long-term sustainability without organizational support. While Ciudad España did have better social health than the former communities in Tegucigalpa, its partnership approach failed to establish emergent norms that would have promoted stronger social health indicators. There was less NGO influence, fewer organizational resources over time, shorter time commitment, and almost no coercive means. Although España has lower social health than Divina, the community has had less conflict and is more independent.
  • Thumbnail Image
    Item
  • Thumbnail Image
    Item
    Running on Fumes: Preventable Public Health Failures and Mishaps Post-Hurricane Maria in Puerto Rico
    (2018-12) Cespedes Perez, Akira
    Emergency preparedness programs that were in place for Puerto Rico when Hurricane Maria struck were disconcerting on a local and national level. After highlighting some of the hurricane’s physical and financial effects on Puerto Rico, I describe the emergency response survivors received in Puerto Rico after Hurricane Maria, or lack thereof. Lack of foresight as well as lack of support from government entities created preventable issues that affected hurricane survivors for months after the storm. I provide recommendations for how some of the pitfalls of emergency relief efforts post Hurricane María could be prevented, including verifying the legitimacy of FEMA contractors, replenishing FEMA warehouses speedily, establishing specific local procedures for disaster relief, and treating hurricane survivors across the nation equally, regardless of their ethnicity or socio-economic status. I also highlight the importance of providing fuel, electric generators, and personnel to restore electricity as soon as possible after a hurricane, given that electricity has become an essential aspect of modern life and an integral component of public health infrastructure, especially in communities with limited resources.
  • Thumbnail Image
    Item