Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 16 of 16 for “"distributional robustness"”.

  1. Distributional robustness: towards challenging and real-world settings of distribution shift

    <p>The ever-evolving world we live in causes continuous data distribution shifts for any machine learning application. As machine learning models are notoriously not robust against such distribution shifts, it is of our interest to develop techniques to deal with this problem. <strong>Hence, this …

    oxford Repository record for Distributional robustness: towards challenging and real-world settings of distribution shift (opens in a new tab)

  2. Model-Based and Data-Driven Covariance Control: Theory and Applications

    … methods often struggle with ensuring safety and robustness in stochastic environments. This dissertation advances the theory of covariance steering (CS), which shifts the focus from controlling specific system states to steering entire state distributions under constraints. Historically, CS has …

    gatech Repository record for Model-Based and Data-Driven Covariance Control: Theory and Applications (opens in a new tab)

  3. Randomized dimension reduction with statistical guarantees

    … augmentation that improve generalization and distributional robustness provably. Specifically, Chapter 4 presents a sample complexity analysis for data augmentation consistency regularization where we view sample efficiency from the lens of dimension reduction in the function space. Then in …

    texas Repository record for Randomized dimension reduction with statistical guarantees (opens in a new tab)

  4. Learning-based intelligent control and safety assurance of unmanned autonomous vehicles

    … demands for multi-agent systems; (iii) robustness—resilience to uncertainty including non-Gaussian disturbances.<br/><br/>A data-driven approach identifies robot dynamics via Sparse Identification of Nonlinear Dynamics (SINDY), superior to NARX in noise robustness. Control Barrier …

    qu-belfast Repository record for Learning-based intelligent control and safety assurance of unmanned autonomous vehicles (opens in a new tab) Embargoed until 2027-07-31

  5. A Systems Approach to the Modeling and Control of Molecular, Microparticle, and Biological Distributions

    … optimal control formulation, and worst-case and distributional robustness analysis. Free radical bulk polymerization is the model system for molecular distributions. In situ ATR-FTIR spectroscopy was used to determine monomer concentration; off-line gel permeation chromatography was used to …

    uiuc Repository record for A Systems Approach to the Modeling and Control of Molecular, Microparticle, and Biological Distributions (opens in a new tab)

  6. A Theory of Generative Models and Robustness via Regularization

    … privacy. We then focus on machine learning robustness, where one is interested in understanding the susceptibility of a model in the face of adversarial threats. We show that regularization is intimately connected to distributional robustness, which subsumes existing results and extends them …

    anu Repository record for A Theory of Generative Models and Robustness via Regularization (opens in a new tab)

  7. Data-driven Distributionally Robust Stochastic Optimization via Wasserstein Distance with Applications to Portfolio Risk Management and Inventory Control

    … dissertation is stochastic optimization under distributional ambiguity. One canthink of this as a two player game between a decision maker, who tries to minimize some loss or maximize some reward, and an adversarial agent that chooses the worst case, or least favorable, distribution (to the …

    umn Repository record for Data-driven Distributionally Robust Stochastic Optimization via Wasserstein Distance with Applications to Portfolio Risk Management and Inventory Control (opens in a new tab)

  8. Machine Learning Toward Materials Discovery: From Crystal Mapping and Out-of-Distribution Property Prediction to Radiation Detection and Emerging Foundation Models.

    … machine learning frameworks to improve robustness, generalization, and interpretability in materials informatics and radiation detection. The work spans crystal structure mapping, adversarial learning for out-of- distribution prediction, foundation-model-based property prediction, and …

    south-carolina Repository record for Machine Learning Toward Materials Discovery: From Crystal Mapping and Out-of-Distribution Property Prediction to Radiation Detection and Emerging Foundation Models. (opens in a new tab)

  9. Towards reliability and interactive debugging for large language models

    … predictions and are robust to data biases or distributional shifts. They also want to be equipped to interact with these models to better understand and debug them. We present a variety of training and inference techniques toward building these aspects of reliability into models. We …

    washington Repository record for Towards reliability and interactive debugging for large language models (opens in a new tab)

  10. Distributionally robust binary classifier under Wasserstein distance

    The robustification of statistical models has been a popular topic for decades. Statistical robustification and robust optimization are the two main approaches in the literature, where the former stabilizes the model output by removing the outlier points while the latter concerns more the outlier …

    calgary Repository record for Distributionally robust binary classifier under Wasserstein distance (opens in a new tab)

  11. Theories and Algorithms for Efficient and Robust Sequential Decision Making

    … (3) learned policies often exhibit brittle robustness, with significant performance degradation under slight environment shift. These obstacles have collectively prevented the widespread deployment of reinforcement learning, particularly in resource-scarce and high-stakes domains. This …

    gatech Repository record for Theories and Algorithms for Efficient and Robust Sequential Decision Making (opens in a new tab)

  12. Certifying robustness in inference and learning problems

    … answered. In this dissertation, a few topics in robustness of inference and learning methods are studied. One of the key issues with data-driven methods in practice is unexpected changes that can occur at inference time potentially affecting the performance of these methods, for instance, …

    uiuc Repository record for Certifying robustness in inference and learning problems (opens in a new tab)

  13. Robust Fragmentation: A Data-Driven Approach to Decision-Making Under Distributional Ambiguity

    … an unknown distribution leading to the term distributional ambiguity. The decision maker may only have a sample of past events to guide them in balancing the costs and benefits of every possibility. Such limited historical data can help to provide guidance, but how best to use it? One would …

    umn Repository record for Robust Fragmentation: A Data-Driven Approach to Decision-Making Under Distributional Ambiguity (opens in a new tab)

  14. Estimating selected disaggregated socio-economic indicators using small area estimation techniques

    … the distribution of the random effects and distributional robustness is automatically achieved. The MSE is estimated using an analytical approach based on Taylor series linearization. Chapter 3 presents the estimation of overweight prevalence at the county level in Kenya. In this …

    fu-berlin Repository record for Estimating selected disaggregated socio-economic indicators using small area estimation techniques (opens in a new tab)