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 20 of 27 for “"Robust loss"”.

  1. Robust Approaches for Matrix-Valued Parameters

    … matrix-valued parameters with a focus on their robustness properties in the presence of outliers. We propose a general framework for robust modeling with matrix-valued parameters by minimizing robust loss functions with penalization. However, there are challenges to this approach in both …

    temple Repository record for Robust Approaches for Matrix-Valued Parameters (opens in a new tab)

  2. Novel Examination of Interpretable Surrogates and Adversarial Robustness in Machine Learning

    … Hence, we carefully argue that adversarial robustness should be defined as a locally adaptive measure complying with the underlying distribution. We then suggest a definition for an adaptive robust loss, an empirical version of it and a resulting data-augmentation framework.

    york Repository record for Novel Examination of Interpretable Surrogates and Adversarial Robustness in Machine Learning (opens in a new tab)

  3. Robust Low-Rank Tensor Discriminant Analysis With Optimal Scoring

    Robust discriminant analysis with optimal scoring has been shown effective for classifying high-dimensional matrix data, particularly in the context of two-dimensional images. The proposed method presents an extension of the Multi-Projection Optimal Scoring Discriminant Analysis framework …

    ucf Repository record for Robust Low-Rank Tensor Discriminant Analysis With Optimal Scoring (opens in a new tab)

  4. Adaptive Volatility Forecasting Models

    … forecasts were analyzed using the two most robust loss functions MSE and QLIKE (Patton 2011). After forecasting losses were calculated, the MCS Test proposed by Hansen et al. in 2011 was used to identify which models significantly out performed their peers. Results show that adaptive …

    calpoly Repository record for Adaptive Volatility Forecasting Models (opens in a new tab)

  5. Data-driven Fault Detection and Diagnosis Frameworks for HVAC Systems using Probabilistic and Deep Generative Models

    … principal component analyzers (NN-MPPCA) with a robust loss function for enhanced anomaly detection; a new framework combining variational autoencoders (VAE) with NN-MPPCA to handle high-dimensional data and incomplete datasets; and the adaptive adversarial autoencoder (AdaAAE), which refines …

    concordia Download PDF for Data-driven Fault Detection and Diagnosis Frameworks for HVAC Systems using Probabilistic and Deep Generative Models (opens in a new tab)

  6. Investigating The Role of The P63 Isoform Δnp63 In Lung Stem Cell Populations and Lung Cancer

    … indicate that deletion of ΔNp63 results in robust loss of enhancer histone marks at cell identity genes for lung progenitor populations of basal cells and AT2 cells. Analysis of ΔNp63-regulated pathways uncovered that ΔNp63 regulates cell-type-specific genes as well as common genes for basal …

    uthsc Repository record for Investigating The Role of The P63 Isoform Δnp63 In Lung Stem Cell Populations and Lung Cancer (opens in a new tab)

  7. Few-shot 3D Novel View Synthesis with Depth Guidance

    … from depth. We firstly apply a depth-supervision loss that directly penalizes deviations between rendered and ground-truth depths, which works well for the NeRF model under sparse-view conditions. Considering the efficiency of 3DGS, we next apply our depth-aware optimization framework to 3DGS, a …

    unsw Repository record for Few-shot 3D Novel View Synthesis with Depth Guidance (opens in a new tab)

  8. Few-shot 3D Novel View Synthesis with Depth Guidance

    … from depth. We firstly apply a depth-supervision loss that directly penalizes deviations between rendered and ground-truth depths, which works well for the NeRF model under sparse-view conditions. Considering the efficiency of 3DGS, we next apply our depth-aware optimization framework to 3DGS, a …

    unsw Repository record for Few-shot 3D Novel View Synthesis with Depth Guidance (opens in a new tab)

  9. A Concave Pairwise Fusion Approach to Clustering of Multi-Response Regression and Its Robust Extensions

    … improved. In the second part, we introduce robust solutions to our proposed work. We introduce two approaches to handle outliers or long-tail distributions. The first is to replace the squared loss with robust loss, among which are absolute loss and Huber loss. The second is to characterize …

    temple Repository record for A Concave Pairwise Fusion Approach to Clustering of Multi-Response Regression and Its Robust Extensions (opens in a new tab)

  10. Adaptive Estimation using Gaussian Mixtures

    This thesis offers a probabilistic solution to robust estimation using a novel adaptive estimator. Reliable state estimation is a mandatory prerequisite for autonomous systems interacting with the real world. The presence of outliers challenges the Gaussian assumption of numerous estimation …

    qucosa-diss

  11. Automated Machine Learning with Constraints and Imperfect Data

    … constraints, such as model size, fairness, and robustness complicates the AutoML flow. When computing resources are insufficient, small search space constrains the flexibility to search neural networks, which causes inconsistent architectures used in search and evaluation stages. In this …

    tamu Repository record for Automated Machine Learning with Constraints and Imperfect Data (opens in a new tab)

  12. Noise and Information in Deep Learning: A Statistical Physics Perspective on Learning and Neural Representations

    … applications raises concerns about their robustness and interpretability. Since these models consist of large weight matrices, random matrix theory (RMT) provides a natural framework for analysis. In this thesis, we study how information is stored in the model’s weight matrices by …

    qucosa-diss

  13. Robust Approaches for Learning with Noisy Labels

    … the model from memorizing them; 4) EM-enhanced loss: a family of robust loss functions that not only mitigates the influence of noisy labels, but also avoids underfitting problem; 5) MixNN: a framework that trains the model with new synthetic samples to mitigate the impact of noisy labels. Our …

    mcmaster Repository record for Robust Approaches for Learning with Noisy Labels (opens in a new tab)

  14. Towards Robust Deep Learning: Label Noise Modeling, Algorithms, and Applications

    This thesis investigates robust and hybrid deep learning with emphasis on improving accuracy and generalization in challenging real-world settings, including learning under noisy supervision and applications to complex scientific data. In the first part, we address instance-dependent label noise by …

    ucf Repository record for Towards Robust Deep Learning: Label Noise Modeling, Algorithms, and Applications (opens in a new tab)

  15. Robust approaches and optimization for 3D data

    We introduce a robust, purely geometric, representation framework for fundamental association and analysis problems involving multiple views and scenes. The framework utilizes surface patches / segments as the underlying data unit, and is capable of effectively harnessing macro scale 3D geometry in …

    gatech Repository record for Robust approaches and optimization for 3D data (opens in a new tab)

  16. Advances in robust signal processing and applications

    Robust signal processing and machine learning methodologies are critical for the reliable operation of modern technological systems, particularly in dynamic and uncertain environments such as the Internet of Things (IoT). However, system performance is often compromised by pervasive challenges, …

    aalto Repository record for Advances in robust signal processing and applications (opens in a new tab)

  17. Information Recovery With Missing Data When Outcomes Are Right Censored.

    … are non-parametric methods that use reduction in loss to partition the covariate space into binary partitions creating a prediction model that is easily interpreted and visualized. When some observations are censored the full data loss function is not a function of the observed data and Molinaro …

    cornell Repository record for Information Recovery With Missing Data When Outcomes Are Right Censored. (opens in a new tab)

  18. Trip with TRP: CNI-1 and SEC-24.2 act as TRP-4 channel trafficking regulators in Caenorhabditis elegans

    … this mutation leads to a progressive and robust loss of dopaminergic neurons. Gain-of-function mutations in ion channels with easily detectable phenotypes such as neurodegeneration, offer a unique opportunity to identify neuroprotective genes, including regulators of channel function. A …

    edinburgh Repository record for Trip with TRP: CNI-1 and SEC-24.2 act as TRP-4 channel trafficking regulators in Caenorhabditis elegans (opens in a new tab)

  19. Lasso-type sparse regression and high-dimensional Gaussian graphical models

    … ratio is low: (i) to leverage adaptive robust loss functions; (ii) to adopt a fully Bayesian modeling framework. In solution (i), we propose a robust Lasso with convex combined loss function and study its asymptotic behaviors. We further extend the asymptotic analysis to the Huberized …

    ubc Repository record for Lasso-type sparse regression and high-dimensional Gaussian graphical models (opens in a new tab) Download PDF for Lasso-type sparse regression and high-dimensional Gaussian graphical models (opens in a new tab)

  20. The Anti-Tumor Effects Of Hur Inhibition In Glioblastoma

    … on GBM development. In this model, we found robust loss of HuR in brain resident microglia and tumor infiltrated macrophages. HuR knockout significantly prolonged survival of tumor-bearing mice, as a result of decreased tumor proliferation and attenuated immunosuppression in the tumor …

    uab Repository record for The Anti-Tumor Effects Of Hur Inhibition In Glioblastoma (opens in a new tab)

Page 1 of 2