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"”.
-
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 …
-
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.
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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, …
-
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 …
-
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 …
-
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 …
-
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 …
Page 1 of 2